注意
点击 这里 下载完整示例代码
摆锤：使用TorchRL编写您的环境和转换¶
创建日期: 2023年11月09日 | 最后更新日期: 2024年02月05日 | 最后验证日期: 2024年11月05日
作者: Vincent Moens
创建一个环境（一个模拟器或与物理控制系统交互的接口）是强化学习和控制工程的一个整合部分。
TorchRL 提供了一组工具，可以在多种情况下使用。 本教程演示了如何从头开始使用 PyTorch 和 TorchRL 编写一个摆锤模拟器。 它受到了 OpenAI-Gym/Farama-Gymnasium 控制库 中 Pendulum-v1 实现的启发。
单摆模型¶
核心收获：
在TorchRL中设计环境的方法： - 编写规范（输入、观察和奖励）； - 实现行为：初始化、重置和步骤。
转换您的环境输入和输出，并编写自己的变换。
如何使用
TensorDict通过codebase传递任意数据结构 。在这一过程中，我们将接触 TorchRL 的三个关键组件：
为了给您一个使用TorchRL的环境可以实现什么的直观感受，我们将设计一个无状态环境。与维护最新物理状态并依赖此状态进行状态间转换的有状态环境不同，无状态环境在每一步期望当前状态和采取的动作被提供给他们。TorchRL 支持这两种类型的环境，但无状态环境更为通用，因此能够覆盖TorchRL环境API更广泛的功能。
无状态环境的建模使用户完全控制模拟器的输入和输出：可以在实验的任何阶段重置实验，或者从外部主动修改动态。然而，这假设我们对任务有一定的控制权，这可能并不总是成立的情况：解决一个无法控制当前状态的问题更具挑战性，但其应用范围要广泛得多。
无状态环境的另一个优点是可以启用过渡模拟的批量执行。如果后端和实现允许的话，一个代数操作可以无缝地在标量、向量或张量上执行。本教程中给出了这样的例子。
本教程将按如下结构进行：
我们首先会熟悉环境属性： 其形状(
batch_size)，其方法(主要是step()，reset()和set_seed()) 最后是其规格。在编写完我们的模拟器之后，我们将演示如何在使用变换进行训练时利用它。
我们将探索 TorchRL 的 API 所带来的新途径，包括：输入转换的可能性、模拟的向量化执行以及通过模拟图进行反向传播的可能性。
最后，我们将训练一个简单的策略来解决我们实现的系统。
from collections import defaultdict
from typing import Optional
import numpy as np
import torch
import tqdm
from tensordict import TensorDict, TensorDictBase
from tensordict.nn import TensorDictModule
from torch import nn
from torchrl.data import BoundedTensorSpec, CompositeSpec, UnboundedContinuousTensorSpec
from torchrl.envs import (
CatTensors,
EnvBase,
Transform,
TransformedEnv,
UnsqueezeTransform,
)
from torchrl.envs.transforms.transforms import _apply_to_composite
from torchrl.envs.utils import check_env_specs, step_mdp
DEFAULT_X = np.pi
DEFAULT_Y = 1.0
在设计新的环境类时，您必须注意四件事：
EnvBase._reset(), 用于在（可能是随机的）初始状态下重置模拟器；EnvBase._step()负责状态转换动态；EnvBase._set_seed`()实现了播种机制；环境规范。
首先，我们描述一下要解决的问题：我们希望对一个可以控制其固定点所施加扭矩的简单摆进行建模。 我们的目标是将摆置于向上位置（约定以角位置为0表示），并使其在该位置静止不动。 为了设计我们的动态系统，我们需要定义两个方程：跟随动作（施加的扭矩）的运动方程以及构成我们目标函数的奖励方程。
对于运动方程，我们将按照以下方式更新角速度：
\[\dot{\theta}_{t+1} = \dot{\theta}_t + (3 * g / (2 * L) * \sin(\theta_t) + 3 / (m * L^2) * u) * dt\]
where \(\dot{\theta}\) 是角速度（单位：rad/sec），\(g\) 是重力加速度，\(L\) 是摆长，\(m\) 是摆的质量，\(\theta\) 是摆的角位置，\(u\) 是扭矩。然后根据上述公式更新角位置。
\[\theta_{t+1} = \theta_{t} + \dot{\theta}_{t+1} dt\]
我们将奖励定义为
\[r = -(\theta^2 + 0.1 * \dot{\theta}^2 + 0.001 * u^2)\]
当角度接近0度（摆锤处于向上位置）、角速度接近0（没有运动）且扭矩也为0时，该值将达到最大。
编码动作的效果：_step()¶
step 方法是首先要考虑的事情，因为它将编码我们感兴趣的模拟。在 TorchRL 中，EnvBase 类有一个 EnvBase.step()
方法，该方法接收一个 tensordict.TensorDict
实例，其中包含一个 "action" 入口，指示要采取什么行动。
为了方便从那个tensordict读写数据，并确保键与库中预期的一致，模拟部分已被委托给一个私有抽象方法_step()，该方法从一个tensordict读取输入数据，并生成一个新的tensordict包含输出数据。
The _step() 方法应该执行以下操作：
Read the input keys (such as
"action") and execute the simulation based on these;Retrieve observations, done state and reward;
Write the set of observation values along with the reward and done state at the corresponding entries in a new
TensorDict.
接下来，step() 方法将会合并 step() 在输入 tensordict 中的输出以确保输入/输出一致性。
通常，在状态ful环境中，这会看起来像这样：
>>> policy(env.reset())
>>> print(tensordict)
TensorDict(
fields={
action: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=cpu,
is_shared=False)
>>> env.step(tensordict)
>>> print(tensordict)
TensorDict(
fields={
action: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
reward: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=cpu,
is_shared=False),
observation: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=cpu,
is_shared=False)
注意根 tensordict 没有改变，唯一的修改是一个新的 "next" 条目包含了新信息。
在单摆示例中，我们的_step()方法将会读取输入tensordict中的相关条目，并计算在由"action"键编码的力作用于单摆之后的新位置和速度。我们根据上一个位置"th"加上新的速度"new_thdot"在时间间隔dt内计算出新的角位置。
自从我们的目标是让摆锤摆到某个位置并保持在那里不动，我们的cost（负面奖励）函数在接近目标且速度较低的位置较低。
确实，我们希望避免那些距离“向上”位置较远和/或速度远离0的位置。
在我们的示例中，EnvBase._step() 被编码为一个静态方法，因为我们的环境是无状态的。在有状态设置中，需要 self 参数，因为状态需要从环境中读取。
def _step(tensordict):
th, thdot = tensordict["th"], tensordict["thdot"] # th := theta
g_force = tensordict["params", "g"]
mass = tensordict["params", "m"]
length = tensordict["params", "l"]
dt = tensordict["params", "dt"]
u = tensordict["action"].squeeze(-1)
u = u.clamp(-tensordict["params", "max_torque"], tensordict["params", "max_torque"])
costs = angle_normalize(th) ** 2 + 0.1 * thdot**2 + 0.001 * (u**2)
new_thdot = (
thdot
+ (3 * g_force / (2 * length) * th.sin() + 3.0 / (mass * length**2) * u) * dt
)
new_thdot = new_thdot.clamp(
-tensordict["params", "max_speed"], tensordict["params", "max_speed"]
)
new_th = th + new_thdot * dt
reward = -costs.view(*tensordict.shape, 1)
done = torch.zeros_like(reward, dtype=torch.bool)
out = TensorDict(
{
"th": new_th,
"thdot": new_thdot,
"params": tensordict["params"],
"reward": reward,
"done": done,
},
tensordict.shape,
)
return out
def angle_normalize(x):
return ((x + torch.pi) % (2 * torch.pi)) - torch.pi
重置模拟器: _reset()¶
我们需要关注的第二种方法是
_reset() 方法。就像
_step()，它也应该在输出的
tensordict 中写入观察条目，并且可能写入一个结束状态（如果省略了结束状态，父方法
reset() 将会将其填充为
False）。在某些上下文中，需要
_reset 方法接收调用它的函数发出的命令（例如，在多智能体设置中，我们可能想要指示哪些智能体需要重置）。这也是为什么
_reset() 方法也需要接收一个
tensordict 作为输入的原因，尽管它可以为空或
None。
父级 EnvBase.reset() 进行一些简单的检查，就像 EnvBase.step() 所做的那样，例如确保在输出 tensordict 中返回一个 "done" 状态，并且形状与规格中预期的相匹配。
对于我们来说，唯一重要的事情是考虑EnvBase._reset()是否包含了所有预期的观测值。再次强调，
由于我们使用的是无状态环境，我们将摆动配置传递给一个嵌套的tensordict，命名为"params"。
在本例中，我们没有传递一个结束状态，因为对于_reset()这不是强制性的，并且我们的环境是非终止的，所以我们总是期望它是False。
def _reset(self, tensordict):
if tensordict is None or tensordict.is_empty():
# if no ``tensordict`` is passed, we generate a single set of hyperparameters
# Otherwise, we assume that the input ``tensordict`` contains all the relevant
# parameters to get started.
tensordict = self.gen_params(batch_size=self.batch_size)
high_th = torch.tensor(DEFAULT_X, device=self.device)
high_thdot = torch.tensor(DEFAULT_Y, device=self.device)
low_th = -high_th
low_thdot = -high_thdot
# for non batch-locked environments, the input ``tensordict`` shape dictates the number
# of simulators run simultaneously. In other contexts, the initial
# random state's shape will depend upon the environment batch-size instead.
th = (
torch.rand(tensordict.shape, generator=self.rng, device=self.device)
* (high_th - low_th)
+ low_th
)
thdot = (
torch.rand(tensordict.shape, generator=self.rng, device=self.device)
* (high_thdot - low_thdot)
+ low_thdot
)
out = TensorDict(
{
"th": th,
"thdot": thdot,
"params": tensordict["params"],
},
batch_size=tensordict.shape,
)
return out
环境元数据： env.*_spec¶
规格定义了环境的输入和输出域。 在运行时，规格需要准确地定义将要接收的张量，因为它们经常用于多进程和分布式设置中传输有关环境的信息。此外，在实际的多进程和分布式系统中，规格还可以用于懒加载定义的神经网络和测试脚本，而无需实际查询环境（例如，对于真实物理系统来说，这可能是昂贵的操作）。
我们必须在我们的环境中编写四个规格：
EnvBase.observation_spec: 这将是一个CompositeSpec实例，其中每个键都是一个观测值（一个CompositeSpec可以 被视为规格字典）。EnvBase.action_spec: 它可以是任何类型的规格，但必须与输入"action"中的第tensordict项相对应；EnvBase.reward_spec: 提供了关于奖励空间的信息；EnvBase.done_spec: 提供了关于done标志空间的信息。
TorchRL 规范分为两个通用容器：input_spec，它包含 step 函数读取的信息的规范（分为 action_spec 包含动作和 state_spec 包含其余所有内容），以及 output_spec，它编码了 step 输出的规范（observation_spec、reward_spec 和 done_spec）。
通常情况下，你不应直接与 output_spec 和 input_spec 交互，而只与其内容交互：observation_spec、reward_spec、done_spec、action_spec 和 state_spec。
原因是这些规范在 output_spec 和 input_spec 中以非平凡的方式组织，并且不应直接修改其中任何一个。
换句话说，observation_spec 及其相关属性是输出和输入规范容器内容的便捷快捷方式。
TorchRL 提供多个 TensorSpec
子类来
编码环境的输入和输出特性。
规格形状¶
环境规范的前向维度必须与环境批次大小匹配。这样做是为了确保每个环境组件（包括其变换）都能准确地表示预期的输入和输出形状。这在状态ful设置中应该准确地进行编码。
对于非批量锁定的环境，例如我们在示例中展示的环境（见下方），这无关紧要，因为环境的批量大小很可能为空。
def _make_spec(self, td_params):
# Under the hood, this will populate self.output_spec["observation"]
self.observation_spec = CompositeSpec(
th=BoundedTensorSpec(
low=-torch.pi,
high=torch.pi,
shape=(),
dtype=torch.float32,
),
thdot=BoundedTensorSpec(
low=-td_params["params", "max_speed"],
high=td_params["params", "max_speed"],
shape=(),
dtype=torch.float32,
),
# we need to add the ``params`` to the observation specs, as we want
# to pass it at each step during a rollout
params=make_composite_from_td(td_params["params"]),
shape=(),
)
# since the environment is stateless, we expect the previous output as input.
# For this, ``EnvBase`` expects some state_spec to be available
self.state_spec = self.observation_spec.clone()
# action-spec will be automatically wrapped in input_spec when
# `self.action_spec = spec` will be called supported
self.action_spec = BoundedTensorSpec(
low=-td_params["params", "max_torque"],
high=td_params["params", "max_torque"],
shape=(1,),
dtype=torch.float32,
)
self.reward_spec = UnboundedContinuousTensorSpec(shape=(*td_params.shape, 1))
def make_composite_from_td(td):
# custom function to convert a ``tensordict`` in a similar spec structure
# of unbounded values.
composite = CompositeSpec(
{
key: make_composite_from_td(tensor)
if isinstance(tensor, TensorDictBase)
else UnboundedContinuousTensorSpec(
dtype=tensor.dtype, device=tensor.device, shape=tensor.shape
)
for key, tensor in td.items()
},
shape=td.shape,
)
return composite
可重复的实验：初始化种子¶
初始化一个环境时，播种是一个常见的操作。
EnvBase._set_seed() 的唯一目标是设置其内部模拟器的种子。如果可能，此操作不应调用 reset() 或与环境执行交互。父级 EnvBase.set_seed() 方法整合了一种机制，允许使用不同的伪随机和可重复种子播种多个环境。
def _set_seed(self, seed: Optional[int]):
rng = torch.manual_seed(seed)
self.rng = rng
Wrapping things together: the EnvBase 类¶
我们终于可以把各个部分组合起来，设计我们的环境类了。
规格初始化需要在环境构建期间进行，因此我们必须确保在
PendulumEnv.__init__() 中调用 _make_spec() 方法。
我们添加一个静态方法 PendulumEnv.gen_params()，该方法在执行期间确定性地生成一组超参数：
def gen_params(g=10.0, batch_size=None) -> TensorDictBase:
"""Returns a ``tensordict`` containing the physical parameters such as gravitational force and torque or speed limits."""
if batch_size is None:
batch_size = []
td = TensorDict(
{
"params": TensorDict(
{
"max_speed": 8,
"max_torque": 2.0,
"dt": 0.05,
"g": g,
"m": 1.0,
"l": 1.0,
},
[],
)
},
[],
)
if batch_size:
td = td.expand(batch_size).contiguous()
return td
我们将环境定义为非batch_locked，通过将homonymous
属性设置为False。这意味着我们不会强制输入
tensordict具有与环境相匹配的batch-size。
以下代码将会把我们上面编写的部分组合在一起。
class PendulumEnv(EnvBase):
metadata = {
"render_modes": ["human", "rgb_array"],
"render_fps": 30,
}
batch_locked = False
def __init__(self, td_params=None, seed=None, device="cpu"):
if td_params is None:
td_params = self.gen_params()
super().__init__(device=device, batch_size=[])
self._make_spec(td_params)
if seed is None:
seed = torch.empty((), dtype=torch.int64).random_().item()
self.set_seed(seed)
# Helpers: _make_step and gen_params
gen_params = staticmethod(gen_params)
_make_spec = _make_spec
# Mandatory methods: _step, _reset and _set_seed
_reset = _reset
_step = staticmethod(_step)
_set_seed = _set_seed
测试我们的环境¶
TorchRL 提供了一个简单的函数 check_env_specs()
来检查一个（转换后的）环境是否有符合其规范的输入/输出结构。
让我们试一下：
env = PendulumEnv()
check_env_specs(env)
我们可以查看我们的规范以获得环境签名的可视化表示。
print("observation_spec:", env.observation_spec)
print("state_spec:", env.state_spec)
print("reward_spec:", env.reward_spec)
observation_spec: CompositeSpec(
th: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
thdot: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
params: CompositeSpec(
max_speed: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.int64,
domain=discrete),
max_torque: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
dt: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
g: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
m: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
l: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
device=cpu,
shape=torch.Size([])),
device=cpu,
shape=torch.Size([]))
state_spec: CompositeSpec(
th: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
thdot: BoundedTensorSpec(
shape=torch.Size([]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous),
params: CompositeSpec(
max_speed: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.int64,
domain=discrete),
max_torque: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
dt: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
g: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
m: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
l: UnboundedContinuousTensorSpec(
shape=torch.Size([]),
space=None,
device=cpu,
dtype=torch.float32,
domain=continuous),
device=cpu,
shape=torch.Size([])),
device=cpu,
shape=torch.Size([]))
reward_spec: UnboundedContinuousTensorSpec(
shape=torch.Size([1]),
space=ContinuousBox(
low=Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, contiguous=True),
high=Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, contiguous=True)),
device=cpu,
dtype=torch.float32,
domain=continuous)
我们可以执行几个命令来检查输出结构是否符合预期。
td = env.reset()
print("reset tensordict", td)
reset tensordict TensorDict(
fields={
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False)
我们可以运行env.rand_step()来随机生成一个动作，来自action_spec领域。由于我们的环境是无状态的，因此必须传递一个包含超参数和当前状态的tensordict。在有状态的上下文中，env.rand_step()同样可以完美工作。
td = env.rand_step(td)
print("random step tensordict", td)
random step tensordict TensorDict(
fields={
action: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False),
terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([]),
device=None,
is_shared=False)
转换环境¶
编写无状态模拟器的环境转换稍微复杂一些：需要在下一次迭代调用meth.step()之前应用逆转换来处理需要在后续迭代中读取的输出条目。
这正是展示TorchRL转换所有功能的理想场景!
例如，在以下转换后的环境中，我们unsqueeze条目
["th", "thdot"] 以便将它们沿最后一个维度堆叠。我们还将它们作为in_keys_inv传递，以便在下一个迭代中将它们作为输入传递时，将其压缩回原始形状。
env = TransformedEnv(
env,
# ``Unsqueeze`` the observations that we will concatenate
UnsqueezeTransform(
unsqueeze_dim=-1,
in_keys=["th", "thdot"],
in_keys_inv=["th", "thdot"],
),
)
编写自定义转换¶
TorchRL 的转换可能无法涵盖在执行完环境后想要执行的所有操作。编写一个转换并不需要太多努力。至于环境设计，在编写一个转换时有两步：
正确把握动态（前向和逆向）；
调整环境规范。
一个转换可以在两种情况下使用：单独使用，它可以作为Module。它也可以附加到一个TransformedEnv使用。类的结构允许在不同的上下文中自定义行为。
一个 Transform 骨架可以总结如下：
class Transform(nn.Module):
def forward(self, tensordict):
...
def _apply_transform(self, tensordict):
...
def _step(self, tensordict):
...
def _call(self, tensordict):
...
def inv(self, tensordict):
...
def _inv_apply_transform(self, tensordict):
...
有三个入口点（forward()，_step() 和 inv()）
，它们都会接收 tensordict.TensorDict 个实例。前两个
最终会通过 in_keys 指定的键，并调用 _apply_transform() 到这些键中的每一个。如果提供了指向的条目，
Transform.out_keys 将会被更新为转换后的值。如果需要执行逆向变换，
类似的数据流将会被执行，但使用的是 Transform.inv() 和
Transform._inv_apply_transform() 方法以及 in_keys_inv 和 out_keys_inv 列表中的键。
以下图表总结了此流程，适用于环境和重放缓存。
Transform API
在某些情况下，一个转换可能不会以统一的方式应用于子集的键，而是在父环境上执行一些操作或处理整个输入 tensordict。
在这种情况下，应重写 _call() 和 forward() 方法，并可以跳过 _apply_transform() 方法。
让我们编写新的转换函数来计算位置角的 sine 和 cosine 值，因为这些值对我们学习策略比原始角度值更有用：
class SinTransform(Transform):
def _apply_transform(self, obs: torch.Tensor) -> None:
return obs.sin()
# The transform must also modify the data at reset time
def _reset(
self, tensordict: TensorDictBase, tensordict_reset: TensorDictBase
) -> TensorDictBase:
return self._call(tensordict_reset)
# _apply_to_composite will execute the observation spec transform across all
# in_keys/out_keys pairs and write the result in the observation_spec which
# is of type ``Composite``
@_apply_to_composite
def transform_observation_spec(self, observation_spec):
return BoundedTensorSpec(
low=-1,
high=1,
shape=observation_spec.shape,
dtype=observation_spec.dtype,
device=observation_spec.device,
)
class CosTransform(Transform):
def _apply_transform(self, obs: torch.Tensor) -> None:
return obs.cos()
# The transform must also modify the data at reset time
def _reset(
self, tensordict: TensorDictBase, tensordict_reset: TensorDictBase
) -> TensorDictBase:
return self._call(tensordict_reset)
# _apply_to_composite will execute the observation spec transform across all
# in_keys/out_keys pairs and write the result in the observation_spec which
# is of type ``Composite``
@_apply_to_composite
def transform_observation_spec(self, observation_spec):
return BoundedTensorSpec(
low=-1,
high=1,
shape=observation_spec.shape,
dtype=observation_spec.dtype,
device=observation_spec.device,
)
t_sin = SinTransform(in_keys=["th"], out_keys=["sin"])
t_cos = CosTransform(in_keys=["th"], out_keys=["cos"])
env.append_transform(t_sin)
env.append_transform(t_cos)
TransformedEnv(
env=PendulumEnv(),
transform=Compose(
UnsqueezeTransform(unsqueeze_dim=-1, in_keys=['th', 'thdot'], out_keys=['th', 'thdot'], in_keys_inv=['th', 'thdot'], out_keys_inv=['th', 'thdot']),
SinTransform(keys=['th']),
CosTransform(keys=['th'])))
拼接观察值到一个“观察”条目中。
del_keys=False 确保我们在下一个迭代中保留这些值。
cat_transform = CatTensors(
in_keys=["sin", "cos", "thdot"], dim=-1, out_key="observation", del_keys=False
)
env.append_transform(cat_transform)
TransformedEnv(
env=PendulumEnv(),
transform=Compose(
UnsqueezeTransform(unsqueeze_dim=-1, in_keys=['th', 'thdot'], out_keys=['th', 'thdot'], in_keys_inv=['th', 'thdot'], out_keys_inv=['th', 'thdot']),
SinTransform(keys=['th']),
CosTransform(keys=['th']),
CatTensors(in_keys=['cos', 'sin', 'thdot'], out_key=observation)))
再次检查我们的环境规范是否与接收到的内容匹配：
check_env_specs(env)
执行一次回放¶
执行一次回放是一系列简单的步骤：
重置环境
当某些条件未满足时：
根据一个策略计算一个动作
根据此操作执行一步
收集数据
make a
MDP步
收集数据并返回
这些操作已经被方便地封装在了rollout()
方法中，我们在这里提供一个简化版本。
def simple_rollout(steps=100):
# preallocate:
data = TensorDict({}, [steps])
# reset
_data = env.reset()
for i in range(steps):
_data["action"] = env.action_spec.rand()
_data = env.step(_data)
data[i] = _data
_data = step_mdp(_data, keep_other=True)
return data
print("data from rollout:", simple_rollout(100))
data from rollout: TensorDict(
fields={
action: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
cos: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
cos: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([100, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
sin: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False),
observation: Tensor(shape=torch.Size([100, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([100]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([100, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([100]),
device=None,
is_shared=False)
批量计算¶
我们的教程最后一个未探索的部分是 TorchRL 提供的批量计算能力。由于我们的环境不对输入数据形状做任何假设，我们可以在数据批次上无缝执行这些计算。更棒的是：对于像我们的摆摆动(Pendulum)这样的非批量锁定环境，我们可以随时更改批次大小而无需重新创建环境。 要做到这一点，我们只需生成具有所需形状的参数即可。
batch_size = 10 # number of environments to be executed in batch
td = env.reset(env.gen_params(batch_size=[batch_size]))
print("reset (batch size of 10)", td)
td = env.rand_step(td)
print("rand step (batch size of 10)", td)
reset (batch size of 10) TensorDict(
fields={
cos: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False)
rand step (batch size of 10) TensorDict(
fields={
action: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
cos: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
cos: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
sin: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
observation: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10]),
device=None,
is_shared=False)
执行一次回放需要我们从回放函数中重置环境，因为我们需要动态定义 batch_size，而这不被 rollout() 支持：
rollout = env.rollout(
3,
auto_reset=False, # we're executing the reset out of the ``rollout`` call
tensordict=env.reset(env.gen_params(batch_size=[batch_size])),
)
print("rollout of len 3 (batch size of 10):", rollout)
rollout of len 3 (batch size of 10): TensorDict(
fields={
action: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
cos: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
next: TensorDict(
fields={
cos: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
done: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
observation: Tensor(shape=torch.Size([10, 3, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False),
reward: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
sin: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False),
observation: Tensor(shape=torch.Size([10, 3, 3]), device=cpu, dtype=torch.float32, is_shared=False),
params: TensorDict(
fields={
dt: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
g: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
l: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
m: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False),
max_speed: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.int64, is_shared=False),
max_torque: Tensor(shape=torch.Size([10, 3]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False),
sin: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
terminated: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
th: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
thdot: Tensor(shape=torch.Size([10, 3, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
batch_size=torch.Size([10, 3]),
device=None,
is_shared=False)
训练一个简单的策略¶
在本例中，我们将使用奖励作为可微分的目标来训练一个简单的策略，例如将其视为负损失。 我们将利用动态系统完全可微分的事实，反向传播通过轨迹回报，并调整策略的权重以直接最大化这一值。当然，在许多情况下，我们所做的假设并不成立，比如可微分系统以及对底层机制的全面访问。
仍然，这是一个非常简单的例子，展示了如何在TorchRL中使用自定义环境编写训练循环。
首先编写策略网络：
torch.manual_seed(0)
env.set_seed(0)
net = nn.Sequential(
nn.LazyLinear(64),
nn.Tanh(),
nn.LazyLinear(64),
nn.Tanh(),
nn.LazyLinear(64),
nn.Tanh(),
nn.LazyLinear(1),
)
policy = TensorDictModule(
net,
in_keys=["observation"],
out_keys=["action"],
)
并且我们的优化器：
optim = torch.optim.Adam(policy.parameters(), lr=2e-3)
训练循环¶
我们将依次进行：
生成一个轨迹
累加奖励
通过这些操作定义的图进行反向传播
裁剪梯度范数并进行优化步骤
重复
在训练循环结束时，我们应该得到一个接近 0 的最终奖励，这表明摆锤已经向上方平衡且状态如预期。
batch_size = 32
pbar = tqdm.tqdm(range(20_000 // batch_size))
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optim, 20_000)
logs = defaultdict(list)
for _ in pbar:
init_td = env.reset(env.gen_params(batch_size=[batch_size]))
rollout = env.rollout(100, policy, tensordict=init_td, auto_reset=False)
traj_return = rollout["next", "reward"].mean()
(-traj_return).backward()
gn = torch.nn.utils.clip_grad_norm_(net.parameters(), 1.0)
optim.step()
optim.zero_grad()
pbar.set_description(
f"reward: {traj_return: 4.4f}, "
f"last reward: {rollout[..., -1]['next', 'reward'].mean(): 4.4f}, gradient norm: {gn: 4.4}"
)
logs["return"].append(traj_return.item())
logs["last_reward"].append(rollout[..., -1]["next", "reward"].mean().item())
scheduler.step()
def plot():
import matplotlib
from matplotlib import pyplot as plt
is_ipython = "inline" in matplotlib.get_backend()
if is_ipython:
from IPython import display
with plt.ion():
plt.figure(figsize=(10, 5))
plt.subplot(1, 2, 1)
plt.plot(logs["return"])
plt.title("returns")
plt.xlabel("iteration")
plt.subplot(1, 2, 2)
plt.plot(logs["last_reward"])
plt.title("last reward")
plt.xlabel("iteration")
if is_ipython:
display.display(plt.gcf())
display.clear_output(wait=True)
plt.show()
plot()
0%| | 0/625 [00:00<?, ?it/s]
reward: -6.0488, last reward: -5.0748, gradient norm: 8.519: 0%| | 0/625 [00:00<?, ?it/s]
reward: -6.0488, last reward: -5.0748, gradient norm: 8.519: 0%| | 1/625 [00:00<01:30, 6.88it/s]
reward: -7.0499, last reward: -7.4472, gradient norm: 5.073: 0%| | 1/625 [00:00<01:30, 6.88it/s]
reward: -7.0499, last reward: -7.4472, gradient norm: 5.073: 0%| | 2/625 [00:00<01:29, 6.96it/s]
reward: -7.0685, last reward: -7.0408, gradient norm: 5.552: 0%| | 2/625 [00:00<01:29, 6.96it/s]
reward: -7.0685, last reward: -7.0408, gradient norm: 5.552: 0%| | 3/625 [00:00<01:28, 7.05it/s]
reward: -6.5154, last reward: -5.9086, gradient norm: 2.527: 0%| | 3/625 [00:00<01:28, 7.05it/s]
reward: -6.5154, last reward: -5.9086, gradient norm: 2.527: 1%| | 4/625 [00:00<01:27, 7.10it/s]
reward: -6.2006, last reward: -5.9385, gradient norm: 8.155: 1%| | 4/625 [00:00<01:27, 7.10it/s]
reward: -6.2006, last reward: -5.9385, gradient norm: 8.155: 1%| | 5/625 [00:00<01:27, 7.13it/s]
reward: -6.2568, last reward: -5.4981, gradient norm: 6.223: 1%| | 5/625 [00:00<01:27, 7.13it/s]
reward: -6.2568, last reward: -5.4981, gradient norm: 6.223: 1%| | 6/625 [00:00<01:26, 7.15it/s]
reward: -5.8929, last reward: -8.4491, gradient norm: 4.581: 1%| | 6/625 [00:00<01:26, 7.15it/s]
reward: -5.8929, last reward: -8.4491, gradient norm: 4.581: 1%|1 | 7/625 [00:00<01:26, 7.17it/s]
reward: -6.3233, last reward: -9.0664, gradient norm: 7.596: 1%|1 | 7/625 [00:01<01:26, 7.17it/s]
reward: -6.3233, last reward: -9.0664, gradient norm: 7.596: 1%|1 | 8/625 [00:01<01:25, 7.19it/s]
reward: -6.1021, last reward: -9.5263, gradient norm: 0.9579: 1%|1 | 8/625 [00:01<01:25, 7.19it/s]
reward: -6.1021, last reward: -9.5263, gradient norm: 0.9579: 1%|1 | 9/625 [00:01<01:25, 7.18it/s]
reward: -6.5807, last reward: -8.8075, gradient norm: 3.212: 1%|1 | 9/625 [00:01<01:25, 7.18it/s]
reward: -6.5807, last reward: -8.8075, gradient norm: 3.212: 2%|1 | 10/625 [00:01<01:25, 7.18it/s]
reward: -6.2009, last reward: -8.5525, gradient norm: 2.914: 2%|1 | 10/625 [00:01<01:25, 7.18it/s]
reward: -6.2009, last reward: -8.5525, gradient norm: 2.914: 2%|1 | 11/625 [00:01<01:25, 7.18it/s]
reward: -6.2894, last reward: -8.0115, gradient norm: 52.06: 2%|1 | 11/625 [00:01<01:25, 7.18it/s]
reward: -6.2894, last reward: -8.0115, gradient norm: 52.06: 2%|1 | 12/625 [00:01<01:25, 7.18it/s]
reward: -6.0977, last reward: -6.1845, gradient norm: 18.09: 2%|1 | 12/625 [00:01<01:25, 7.18it/s]
reward: -6.0977, last reward: -6.1845, gradient norm: 18.09: 2%|2 | 13/625 [00:01<01:25, 7.19it/s]
reward: -6.1830, last reward: -7.4858, gradient norm: 5.233: 2%|2 | 13/625 [00:01<01:25, 7.19it/s]
reward: -6.1830, last reward: -7.4858, gradient norm: 5.233: 2%|2 | 14/625 [00:01<01:25, 7.18it/s]
reward: -6.2863, last reward: -5.0297, gradient norm: 1.464: 2%|2 | 14/625 [00:02<01:25, 7.18it/s]
reward: -6.2863, last reward: -5.0297, gradient norm: 1.464: 2%|2 | 15/625 [00:02<01:24, 7.19it/s]
reward: -6.4617, last reward: -5.5997, gradient norm: 2.904: 2%|2 | 15/625 [00:02<01:24, 7.19it/s]
reward: -6.4617, last reward: -5.5997, gradient norm: 2.904: 3%|2 | 16/625 [00:02<01:24, 7.19it/s]
reward: -6.1647, last reward: -6.0777, gradient norm: 4.901: 3%|2 | 16/625 [00:02<01:24, 7.19it/s]
reward: -6.1647, last reward: -6.0777, gradient norm: 4.901: 3%|2 | 17/625 [00:02<01:24, 7.19it/s]
reward: -6.4709, last reward: -6.6813, gradient norm: 0.8317: 3%|2 | 17/625 [00:02<01:24, 7.19it/s]
reward: -6.4709, last reward: -6.6813, gradient norm: 0.8317: 3%|2 | 18/625 [00:02<01:24, 7.18it/s]
reward: -6.3221, last reward: -6.5554, gradient norm: 1.276: 3%|2 | 18/625 [00:02<01:24, 7.18it/s]
reward: -6.3221, last reward: -6.5554, gradient norm: 1.276: 3%|3 | 19/625 [00:02<01:24, 7.17it/s]
reward: -6.3353, last reward: -7.9999, gradient norm: 4.701: 3%|3 | 19/625 [00:02<01:24, 7.17it/s]
reward: -6.3353, last reward: -7.9999, gradient norm: 4.701: 3%|3 | 20/625 [00:02<01:24, 7.17it/s]
reward: -5.8570, last reward: -7.6656, gradient norm: 5.463: 3%|3 | 20/625 [00:02<01:24, 7.17it/s]
reward: -5.8570, last reward: -7.6656, gradient norm: 5.463: 3%|3 | 21/625 [00:02<01:24, 7.16it/s]
reward: -5.7779, last reward: -6.6911, gradient norm: 6.875: 3%|3 | 21/625 [00:03<01:24, 7.16it/s]
reward: -5.7779, last reward: -6.6911, gradient norm: 6.875: 4%|3 | 22/625 [00:03<01:24, 7.16it/s]
reward: -6.0796, last reward: -5.7082, gradient norm: 5.308: 4%|3 | 22/625 [00:03<01:24, 7.16it/s]
reward: -6.0796, last reward: -5.7082, gradient norm: 5.308: 4%|3 | 23/625 [00:03<01:24, 7.15it/s]
reward: -6.0421, last reward: -6.1496, gradient norm: 12.4: 4%|3 | 23/625 [00:03<01:24, 7.15it/s]
reward: -6.0421, last reward: -6.1496, gradient norm: 12.4: 4%|3 | 24/625 [00:03<01:24, 7.13it/s]
reward: -5.5037, last reward: -5.1755, gradient norm: 22.62: 4%|3 | 24/625 [00:03<01:24, 7.13it/s]
reward: -5.5037, last reward: -5.1755, gradient norm: 22.62: 4%|4 | 25/625 [00:03<01:24, 7.12it/s]
reward: -5.5029, last reward: -4.9454, gradient norm: 3.665: 4%|4 | 25/625 [00:03<01:24, 7.12it/s]
reward: -5.5029, last reward: -4.9454, gradient norm: 3.665: 4%|4 | 26/625 [00:03<01:23, 7.13it/s]
reward: -5.9330, last reward: -6.2118, gradient norm: 5.444: 4%|4 | 26/625 [00:03<01:23, 7.13it/s]
reward: -5.9330, last reward: -6.2118, gradient norm: 5.444: 4%|4 | 27/625 [00:03<01:23, 7.14it/s]
reward: -6.0995, last reward: -6.6294, gradient norm: 11.69: 4%|4 | 27/625 [00:03<01:23, 7.14it/s]
reward: -6.0995, last reward: -6.6294, gradient norm: 11.69: 4%|4 | 28/625 [00:03<01:23, 7.15it/s]
reward: -6.3146, last reward: -7.2909, gradient norm: 5.461: 4%|4 | 28/625 [00:04<01:23, 7.15it/s]
reward: -6.3146, last reward: -7.2909, gradient norm: 5.461: 5%|4 | 29/625 [00:04<01:23, 7.16it/s]
reward: -5.9720, last reward: -6.1298, gradient norm: 19.91: 5%|4 | 29/625 [00:04<01:23, 7.16it/s]
reward: -5.9720, last reward: -6.1298, gradient norm: 19.91: 5%|4 | 30/625 [00:04<01:23, 7.15it/s]
reward: -5.9923, last reward: -7.0345, gradient norm: 3.464: 5%|4 | 30/625 [00:04<01:23, 7.15it/s]
reward: -5.9923, last reward: -7.0345, gradient norm: 3.464: 5%|4 | 31/625 [00:04<01:22, 7.16it/s]
reward: -5.3438, last reward: -4.3688, gradient norm: 2.424: 5%|4 | 31/625 [00:04<01:22, 7.16it/s]
reward: -5.3438, last reward: -4.3688, gradient norm: 2.424: 5%|5 | 32/625 [00:04<01:22, 7.17it/s]
reward: -5.6953, last reward: -4.5233, gradient norm: 3.411: 5%|5 | 32/625 [00:04<01:22, 7.17it/s]
reward: -5.6953, last reward: -4.5233, gradient norm: 3.411: 5%|5 | 33/625 [00:04<01:22, 7.17it/s]
reward: -5.4288, last reward: -2.8011, gradient norm: 10.82: 5%|5 | 33/625 [00:04<01:22, 7.17it/s]
reward: -5.4288, last reward: -2.8011, gradient norm: 10.82: 5%|5 | 34/625 [00:04<01:22, 7.16it/s]
reward: -5.5329, last reward: -4.2677, gradient norm: 15.71: 5%|5 | 34/625 [00:04<01:22, 7.16it/s]
reward: -5.5329, last reward: -4.2677, gradient norm: 15.71: 6%|5 | 35/625 [00:04<01:22, 7.17it/s]
reward: -5.6969, last reward: -3.7010, gradient norm: 1.376: 6%|5 | 35/625 [00:05<01:22, 7.17it/s]
reward: -5.6969, last reward: -3.7010, gradient norm: 1.376: 6%|5 | 36/625 [00:05<01:22, 7.17it/s]
reward: -5.9352, last reward: -4.7707, gradient norm: 15.49: 6%|5 | 36/625 [00:05<01:22, 7.17it/s]
reward: -5.9352, last reward: -4.7707, gradient norm: 15.49: 6%|5 | 37/625 [00:05<01:21, 7.17it/s]
reward: -5.6178, last reward: -4.5646, gradient norm: 3.348: 6%|5 | 37/625 [00:05<01:21, 7.17it/s]
reward: -5.6178, last reward: -4.5646, gradient norm: 3.348: 6%|6 | 38/625 [00:05<01:21, 7.17it/s]
reward: -5.7304, last reward: -3.9407, gradient norm: 4.942: 6%|6 | 38/625 [00:05<01:21, 7.17it/s]
reward: -5.7304, last reward: -3.9407, gradient norm: 4.942: 6%|6 | 39/625 [00:05<01:21, 7.18it/s]
reward: -5.3882, last reward: -3.7604, gradient norm: 9.85: 6%|6 | 39/625 [00:05<01:21, 7.18it/s]
reward: -5.3882, last reward: -3.7604, gradient norm: 9.85: 6%|6 | 40/625 [00:05<01:21, 7.17it/s]
reward: -5.3507, last reward: -2.8928, gradient norm: 1.258: 6%|6 | 40/625 [00:05<01:21, 7.17it/s]
reward: -5.3507, last reward: -2.8928, gradient norm: 1.258: 7%|6 | 41/625 [00:05<01:21, 7.18it/s]
reward: -5.6978, last reward: -4.4641, gradient norm: 4.549: 7%|6 | 41/625 [00:05<01:21, 7.18it/s]
reward: -5.6978, last reward: -4.4641, gradient norm: 4.549: 7%|6 | 42/625 [00:05<01:21, 7.19it/s]
reward: -5.5263, last reward: -3.6047, gradient norm: 2.544: 7%|6 | 42/625 [00:06<01:21, 7.19it/s]
reward: -5.5263, last reward: -3.6047, gradient norm: 2.544: 7%|6 | 43/625 [00:06<01:20, 7.19it/s]
reward: -5.5005, last reward: -4.4136, gradient norm: 11.49: 7%|6 | 43/625 [00:06<01:20, 7.19it/s]
reward: -5.5005, last reward: -4.4136, gradient norm: 11.49: 7%|7 | 44/625 [00:06<01:20, 7.19it/s]
reward: -5.2993, last reward: -6.3222, gradient norm: 32.53: 7%|7 | 44/625 [00:06<01:20, 7.19it/s]
reward: -5.2993, last reward: -6.3222, gradient norm: 32.53: 7%|7 | 45/625 [00:06<01:20, 7.18it/s]
reward: -5.4046, last reward: -5.7314, gradient norm: 7.275: 7%|7 | 45/625 [00:06<01:20, 7.18it/s]
reward: -5.4046, last reward: -5.7314, gradient norm: 7.275: 7%|7 | 46/625 [00:06<01:20, 7.18it/s]
reward: -5.6331, last reward: -4.9318, gradient norm: 6.961: 7%|7 | 46/625 [00:06<01:20, 7.18it/s]
reward: -5.6331, last reward: -4.9318, gradient norm: 6.961: 8%|7 | 47/625 [00:06<01:20, 7.17it/s]
reward: -4.8331, last reward: -4.1604, gradient norm: 26.26: 8%|7 | 47/625 [00:06<01:20, 7.17it/s]
reward: -4.8331, last reward: -4.1604, gradient norm: 26.26: 8%|7 | 48/625 [00:06<01:20, 7.17it/s]
reward: -5.4099, last reward: -4.4761, gradient norm: 8.125: 8%|7 | 48/625 [00:06<01:20, 7.17it/s]
reward: -5.4099, last reward: -4.4761, gradient norm: 8.125: 8%|7 | 49/625 [00:06<01:20, 7.18it/s]
reward: -5.4262, last reward: -3.6363, gradient norm: 2.382: 8%|7 | 49/625 [00:06<01:20, 7.18it/s]
reward: -5.4262, last reward: -3.6363, gradient norm: 2.382: 8%|8 | 50/625 [00:06<01:20, 7.18it/s]
reward: -5.3593, last reward: -5.7377, gradient norm: 22.62: 8%|8 | 50/625 [00:07<01:20, 7.18it/s]
reward: -5.3593, last reward: -5.7377, gradient norm: 22.62: 8%|8 | 51/625 [00:07<01:19, 7.19it/s]
reward: -5.2847, last reward: -3.3443, gradient norm: 2.867: 8%|8 | 51/625 [00:07<01:19, 7.19it/s]
reward: -5.2847, last reward: -3.3443, gradient norm: 2.867: 8%|8 | 52/625 [00:07<01:19, 7.18it/s]
reward: -5.3592, last reward: -6.4760, gradient norm: 8.441: 8%|8 | 52/625 [00:07<01:19, 7.18it/s]
reward: -5.3592, last reward: -6.4760, gradient norm: 8.441: 8%|8 | 53/625 [00:07<01:19, 7.18it/s]
reward: -5.9950, last reward: -10.8021, gradient norm: 11.77: 8%|8 | 53/625 [00:07<01:19, 7.18it/s]
reward: -5.9950, last reward: -10.8021, gradient norm: 11.77: 9%|8 | 54/625 [00:07<01:19, 7.18it/s]
reward: -6.3528, last reward: -7.1214, gradient norm: 7.708: 9%|8 | 54/625 [00:07<01:19, 7.18it/s]
reward: -6.3528, last reward: -7.1214, gradient norm: 7.708: 9%|8 | 55/625 [00:07<01:19, 7.18it/s]
reward: -6.4023, last reward: -7.3583, gradient norm: 9.041: 9%|8 | 55/625 [00:07<01:19, 7.18it/s]
reward: -6.4023, last reward: -7.3583, gradient norm: 9.041: 9%|8 | 56/625 [00:07<01:19, 7.17it/s]
reward: -6.3801, last reward: -7.0310, gradient norm: 120.1: 9%|8 | 56/625 [00:07<01:19, 7.17it/s]
reward: -6.3801, last reward: -7.0310, gradient norm: 120.1: 9%|9 | 57/625 [00:07<01:19, 7.17it/s]
reward: -6.4244, last reward: -6.2039, gradient norm: 15.48: 9%|9 | 57/625 [00:08<01:19, 7.17it/s]
reward: -6.4244, last reward: -6.2039, gradient norm: 15.48: 9%|9 | 58/625 [00:08<01:19, 7.17it/s]
reward: -6.4850, last reward: -6.8748, gradient norm: 4.706: 9%|9 | 58/625 [00:08<01:19, 7.17it/s]
reward: -6.4850, last reward: -6.8748, gradient norm: 4.706: 9%|9 | 59/625 [00:08<01:19, 7.16it/s]
reward: -6.4897, last reward: -5.9210, gradient norm: 11.63: 9%|9 | 59/625 [00:08<01:19, 7.16it/s]
reward: -6.4897, last reward: -5.9210, gradient norm: 11.63: 10%|9 | 60/625 [00:08<01:18, 7.17it/s]
reward: -6.2299, last reward: -7.8964, gradient norm: 13.35: 10%|9 | 60/625 [00:08<01:18, 7.17it/s]
reward: -6.2299, last reward: -7.8964, gradient norm: 13.35: 10%|9 | 61/625 [00:08<01:18, 7.17it/s]
reward: -6.0832, last reward: -9.3934, gradient norm: 4.456: 10%|9 | 61/625 [00:08<01:18, 7.17it/s]
reward: -6.0832, last reward: -9.3934, gradient norm: 4.456: 10%|9 | 62/625 [00:08<01:18, 7.17it/s]
reward: -5.8971, last reward: -10.2933, gradient norm: 10.74: 10%|9 | 62/625 [00:08<01:18, 7.17it/s]
reward: -5.8971, last reward: -10.2933, gradient norm: 10.74: 10%|# | 63/625 [00:08<01:18, 7.16it/s]
reward: -5.3377, last reward: -4.6996, gradient norm: 23.29: 10%|# | 63/625 [00:08<01:18, 7.16it/s]
reward: -5.3377, last reward: -4.6996, gradient norm: 23.29: 10%|# | 64/625 [00:08<01:18, 7.16it/s]
reward: -5.2274, last reward: -2.8916, gradient norm: 4.098: 10%|# | 64/625 [00:09<01:18, 7.16it/s]
reward: -5.2274, last reward: -2.8916, gradient norm: 4.098: 10%|# | 65/625 [00:09<01:18, 7.15it/s]
reward: -5.2660, last reward: -4.9110, gradient norm: 12.28: 10%|# | 65/625 [00:09<01:18, 7.15it/s]
reward: -5.2660, last reward: -4.9110, gradient norm: 12.28: 11%|# | 66/625 [00:09<01:18, 7.12it/s]
reward: -5.4503, last reward: -5.6956, gradient norm: 12.22: 11%|# | 66/625 [00:09<01:18, 7.12it/s]
reward: -5.4503, last reward: -5.6956, gradient norm: 12.22: 11%|# | 67/625 [00:09<01:18, 7.09it/s]
reward: -5.9172, last reward: -5.4026, gradient norm: 7.946: 11%|# | 67/625 [00:09<01:18, 7.09it/s]
reward: -5.9172, last reward: -5.4026, gradient norm: 7.946: 11%|# | 68/625 [00:09<01:18, 7.10it/s]
reward: -5.9229, last reward: -4.5205, gradient norm: 6.294: 11%|# | 68/625 [00:09<01:18, 7.10it/s]
reward: -5.9229, last reward: -4.5205, gradient norm: 6.294: 11%|#1 | 69/625 [00:09<01:18, 7.11it/s]
reward: -5.8872, last reward: -5.6637, gradient norm: 8.019: 11%|#1 | 69/625 [00:09<01:18, 7.11it/s]
reward: -5.8872, last reward: -5.6637, gradient norm: 8.019: 11%|#1 | 70/625 [00:09<01:17, 7.12it/s]
reward: -5.9281, last reward: -4.2082, gradient norm: 5.724: 11%|#1 | 70/625 [00:09<01:17, 7.12it/s]
reward: -5.9281, last reward: -4.2082, gradient norm: 5.724: 11%|#1 | 71/625 [00:09<01:17, 7.13it/s]
reward: -5.8561, last reward: -5.6574, gradient norm: 8.357: 11%|#1 | 71/625 [00:10<01:17, 7.13it/s]
reward: -5.8561, last reward: -5.6574, gradient norm: 8.357: 12%|#1 | 72/625 [00:10<01:17, 7.14it/s]
reward: -5.4138, last reward: -4.5230, gradient norm: 7.385: 12%|#1 | 72/625 [00:10<01:17, 7.14it/s]
reward: -5.4138, last reward: -4.5230, gradient norm: 7.385: 12%|#1 | 73/625 [00:10<01:17, 7.14it/s]
reward: -5.4065, last reward: -5.5642, gradient norm: 9.921: 12%|#1 | 73/625 [00:10<01:17, 7.14it/s]
reward: -5.4065, last reward: -5.5642, gradient norm: 9.921: 12%|#1 | 74/625 [00:10<01:17, 7.15it/s]
reward: -4.9786, last reward: -3.2894, gradient norm: 32.73: 12%|#1 | 74/625 [00:10<01:17, 7.15it/s]
reward: -4.9786, last reward: -3.2894, gradient norm: 32.73: 12%|#2 | 75/625 [00:10<01:16, 7.16it/s]
reward: -5.4129, last reward: -7.5831, gradient norm: 9.266: 12%|#2 | 75/625 [00:10<01:16, 7.16it/s]
reward: -5.4129, last reward: -7.5831, gradient norm: 9.266: 12%|#2 | 76/625 [00:10<01:16, 7.16it/s]
reward: -5.7723, last reward: -7.4152, gradient norm: 5.608: 12%|#2 | 76/625 [00:10<01:16, 7.16it/s]
reward: -5.7723, last reward: -7.4152, gradient norm: 5.608: 12%|#2 | 77/625 [00:10<01:16, 7.15it/s]
reward: -6.1604, last reward: -8.0898, gradient norm: 4.389: 12%|#2 | 77/625 [00:10<01:16, 7.15it/s]
reward: -6.1604, last reward: -8.0898, gradient norm: 4.389: 12%|#2 | 78/625 [00:10<01:16, 7.16it/s]
reward: -6.5155, last reward: -5.5376, gradient norm: 36.34: 12%|#2 | 78/625 [00:11<01:16, 7.16it/s]
reward: -6.5155, last reward: -5.5376, gradient norm: 36.34: 13%|#2 | 79/625 [00:11<01:16, 7.16it/s]
reward: -6.5616, last reward: -6.4094, gradient norm: 8.283: 13%|#2 | 79/625 [00:11<01:16, 7.16it/s]
reward: -6.5616, last reward: -6.4094, gradient norm: 8.283: 13%|#2 | 80/625 [00:11<01:16, 7.15it/s]
reward: -6.5333, last reward: -7.4803, gradient norm: 5.895: 13%|#2 | 80/625 [00:11<01:16, 7.15it/s]
reward: -6.5333, last reward: -7.4803, gradient norm: 5.895: 13%|#2 | 81/625 [00:11<01:16, 7.16it/s]
reward: -6.6566, last reward: -5.2588, gradient norm: 7.662: 13%|#2 | 81/625 [00:11<01:16, 7.16it/s]
reward: -6.6566, last reward: -5.2588, gradient norm: 7.662: 13%|#3 | 82/625 [00:11<01:15, 7.15it/s]
reward: -6.4732, last reward: -6.7503, gradient norm: 6.068: 13%|#3 | 82/625 [00:11<01:15, 7.15it/s]
reward: -6.4732, last reward: -6.7503, gradient norm: 6.068: 13%|#3 | 83/625 [00:11<01:15, 7.13it/s]
reward: -6.0714, last reward: -7.3370, gradient norm: 8.059: 13%|#3 | 83/625 [00:11<01:15, 7.13it/s]
reward: -6.0714, last reward: -7.3370, gradient norm: 8.059: 13%|#3 | 84/625 [00:11<01:15, 7.14it/s]
reward: -5.8612, last reward: -6.1915, gradient norm: 9.3: 13%|#3 | 84/625 [00:11<01:15, 7.14it/s]
reward: -5.8612, last reward: -6.1915, gradient norm: 9.3: 14%|#3 | 85/625 [00:11<01:15, 7.16it/s]
reward: -5.3855, last reward: -5.0349, gradient norm: 15.2: 14%|#3 | 85/625 [00:12<01:15, 7.16it/s]
reward: -5.3855, last reward: -5.0349, gradient norm: 15.2: 14%|#3 | 86/625 [00:12<01:15, 7.14it/s]
reward: -4.9644, last reward: -3.4538, gradient norm: 3.445: 14%|#3 | 86/625 [00:12<01:15, 7.14it/s]
reward: -4.9644, last reward: -3.4538, gradient norm: 3.445: 14%|#3 | 87/625 [00:12<01:15, 7.15it/s]
reward: -5.0392, last reward: -4.4080, gradient norm: 11.45: 14%|#3 | 87/625 [00:12<01:15, 7.15it/s]
reward: -5.0392, last reward: -4.4080, gradient norm: 11.45: 14%|#4 | 88/625 [00:12<01:14, 7.16it/s]
reward: -5.1648, last reward: -5.9599, gradient norm: 143.4: 14%|#4 | 88/625 [00:12<01:14, 7.16it/s]
reward: -5.1648, last reward: -5.9599, gradient norm: 143.4: 14%|#4 | 89/625 [00:12<01:14, 7.19it/s]
reward: -5.4284, last reward: -5.5946, gradient norm: 10.3: 14%|#4 | 89/625 [00:12<01:14, 7.19it/s]
reward: -5.4284, last reward: -5.5946, gradient norm: 10.3: 14%|#4 | 90/625 [00:12<01:14, 7.19it/s]
reward: -5.2590, last reward: -5.9181, gradient norm: 11.15: 14%|#4 | 90/625 [00:12<01:14, 7.19it/s]
reward: -5.2590, last reward: -5.9181, gradient norm: 11.15: 15%|#4 | 91/625 [00:12<01:14, 7.19it/s]
reward: -5.4621, last reward: -5.9075, gradient norm: 8.674: 15%|#4 | 91/625 [00:12<01:14, 7.19it/s]
reward: -5.4621, last reward: -5.9075, gradient norm: 8.674: 15%|#4 | 92/625 [00:12<01:14, 7.20it/s]
reward: -5.1772, last reward: -4.9444, gradient norm: 8.351: 15%|#4 | 92/625 [00:12<01:14, 7.20it/s]
reward: -5.1772, last reward: -4.9444, gradient norm: 8.351: 15%|#4 | 93/625 [00:12<01:13, 7.20it/s]
reward: -4.9391, last reward: -4.5595, gradient norm: 8.1: 15%|#4 | 93/625 [00:13<01:13, 7.20it/s]
reward: -4.9391, last reward: -4.5595, gradient norm: 8.1: 15%|#5 | 94/625 [00:13<01:13, 7.20it/s]
reward: -4.8673, last reward: -4.6240, gradient norm: 14.43: 15%|#5 | 94/625 [00:13<01:13, 7.20it/s]
reward: -4.8673, last reward: -4.6240, gradient norm: 14.43: 15%|#5 | 95/625 [00:13<01:13, 7.20it/s]
reward: -4.5919, last reward: -5.0018, gradient norm: 26.09: 15%|#5 | 95/625 [00:13<01:13, 7.20it/s]
reward: -4.5919, last reward: -5.0018, gradient norm: 26.09: 15%|#5 | 96/625 [00:13<01:13, 7.20it/s]
reward: -5.1071, last reward: -3.9127, gradient norm: 2.251: 15%|#5 | 96/625 [00:13<01:13, 7.20it/s]
reward: -5.1071, last reward: -3.9127, gradient norm: 2.251: 16%|#5 | 97/625 [00:13<01:13, 7.20it/s]
reward: -4.9799, last reward: -5.3131, gradient norm: 19.65: 16%|#5 | 97/625 [00:13<01:13, 7.20it/s]
reward: -4.9799, last reward: -5.3131, gradient norm: 19.65: 16%|#5 | 98/625 [00:13<01:13, 7.21it/s]
reward: -4.9612, last reward: -3.9705, gradient norm: 12.55: 16%|#5 | 98/625 [00:13<01:13, 7.21it/s]
reward: -4.9612, last reward: -3.9705, gradient norm: 12.55: 16%|#5 | 99/625 [00:13<01:12, 7.21it/s]
reward: -4.8741, last reward: -4.2230, gradient norm: 6.19: 16%|#5 | 99/625 [00:13<01:12, 7.21it/s]
reward: -4.8741, last reward: -4.2230, gradient norm: 6.19: 16%|#6 | 100/625 [00:13<01:12, 7.21it/s]
reward: -5.0972, last reward: -5.0337, gradient norm: 11.86: 16%|#6 | 100/625 [00:14<01:12, 7.21it/s]
reward: -5.0972, last reward: -5.0337, gradient norm: 11.86: 16%|#6 | 101/625 [00:14<01:12, 7.21it/s]
reward: -5.0350, last reward: -5.0654, gradient norm: 10.83: 16%|#6 | 101/625 [00:14<01:12, 7.21it/s]
reward: -5.0350, last reward: -5.0654, gradient norm: 10.83: 16%|#6 | 102/625 [00:14<01:12, 7.21it/s]
reward: -5.2441, last reward: -4.4596, gradient norm: 7.362: 16%|#6 | 102/625 [00:14<01:12, 7.21it/s]
reward: -5.2441, last reward: -4.4596, gradient norm: 7.362: 16%|#6 | 103/625 [00:14<01:12, 7.21it/s]
reward: -5.1664, last reward: -5.4362, gradient norm: 8.171: 16%|#6 | 103/625 [00:14<01:12, 7.21it/s]
reward: -5.1664, last reward: -5.4362, gradient norm: 8.171: 17%|#6 | 104/625 [00:14<01:12, 7.21it/s]
reward: -5.4041, last reward: -5.6907, gradient norm: 7.77: 17%|#6 | 104/625 [00:14<01:12, 7.21it/s]
reward: -5.4041, last reward: -5.6907, gradient norm: 7.77: 17%|#6 | 105/625 [00:14<01:12, 7.20it/s]
reward: -5.4664, last reward: -6.2760, gradient norm: 11.19: 17%|#6 | 105/625 [00:14<01:12, 7.20it/s]
reward: -5.4664, last reward: -6.2760, gradient norm: 11.19: 17%|#6 | 106/625 [00:14<01:12, 7.18it/s]
reward: -5.0299, last reward: -3.9712, gradient norm: 9.349: 17%|#6 | 106/625 [00:14<01:12, 7.18it/s]
reward: -5.0299, last reward: -3.9712, gradient norm: 9.349: 17%|#7 | 107/625 [00:14<01:12, 7.17it/s]
reward: -4.3332, last reward: -2.4479, gradient norm: 5.772: 17%|#7 | 107/625 [00:15<01:12, 7.17it/s]
reward: -4.3332, last reward: -2.4479, gradient norm: 5.772: 17%|#7 | 108/625 [00:15<01:12, 7.16it/s]
reward: -4.4357, last reward: -2.9591, gradient norm: 4.543: 17%|#7 | 108/625 [00:15<01:12, 7.16it/s]
reward: -4.4357, last reward: -2.9591, gradient norm: 4.543: 17%|#7 | 109/625 [00:15<01:11, 7.17it/s]
reward: -4.6216, last reward: -3.1353, gradient norm: 4.692: 17%|#7 | 109/625 [00:15<01:11, 7.17it/s]
reward: -4.6216, last reward: -3.1353, gradient norm: 4.692: 18%|#7 | 110/625 [00:15<01:11, 7.18it/s]
reward: -4.6261, last reward: -3.7086, gradient norm: 4.496: 18%|#7 | 110/625 [00:15<01:11, 7.18it/s]
reward: -4.6261, last reward: -3.7086, gradient norm: 4.496: 18%|#7 | 111/625 [00:15<01:11, 7.15it/s]
reward: -4.7758, last reward: -5.9818, gradient norm: 21.71: 18%|#7 | 111/625 [00:15<01:11, 7.15it/s]
reward: -4.7758, last reward: -5.9818, gradient norm: 21.71: 18%|#7 | 112/625 [00:15<01:11, 7.15it/s]
reward: -4.7772, last reward: -7.5055, gradient norm: 62.86: 18%|#7 | 112/625 [00:15<01:11, 7.15it/s]
reward: -4.7772, last reward: -7.5055, gradient norm: 62.86: 18%|#8 | 113/625 [00:15<01:11, 7.15it/s]
reward: -4.5840, last reward: -5.3180, gradient norm: 18.74: 18%|#8 | 113/625 [00:15<01:11, 7.15it/s]
reward: -4.5840, last reward: -5.3180, gradient norm: 18.74: 18%|#8 | 114/625 [00:15<01:11, 7.15it/s]
reward: -4.2976, last reward: -3.2083, gradient norm: 10.63: 18%|#8 | 114/625 [00:16<01:11, 7.15it/s]
reward: -4.2976, last reward: -3.2083, gradient norm: 10.63: 18%|#8 | 115/625 [00:16<01:11, 7.14it/s]
reward: -4.5275, last reward: -3.6873, gradient norm: 15.65: 18%|#8 | 115/625 [00:16<01:11, 7.14it/s]
reward: -4.5275, last reward: -3.6873, gradient norm: 15.65: 19%|#8 | 116/625 [00:16<01:11, 7.13it/s]
reward: -4.4107, last reward: -3.1624, gradient norm: 19.7: 19%|#8 | 116/625 [00:16<01:11, 7.13it/s]
reward: -4.4107, last reward: -3.1624, gradient norm: 19.7: 19%|#8 | 117/625 [00:16<01:11, 7.15it/s]
reward: -4.6372, last reward: -3.2571, gradient norm: 15.83: 19%|#8 | 117/625 [00:16<01:11, 7.15it/s]
reward: -4.6372, last reward: -3.2571, gradient norm: 15.83: 19%|#8 | 118/625 [00:16<01:10, 7.15it/s]
reward: -4.4039, last reward: -4.4428, gradient norm: 13.06: 19%|#8 | 118/625 [00:16<01:10, 7.15it/s]
reward: -4.4039, last reward: -4.4428, gradient norm: 13.06: 19%|#9 | 119/625 [00:16<01:11, 7.13it/s]
reward: -4.4728, last reward: -3.5628, gradient norm: 12.04: 19%|#9 | 119/625 [00:16<01:11, 7.13it/s]
reward: -4.4728, last reward: -3.5628, gradient norm: 12.04: 19%|#9 | 120/625 [00:16<01:10, 7.12it/s]
reward: -4.6767, last reward: -5.2466, gradient norm: 6.522: 19%|#9 | 120/625 [00:16<01:10, 7.12it/s]
reward: -4.6767, last reward: -5.2466, gradient norm: 6.522: 19%|#9 | 121/625 [00:16<01:10, 7.12it/s]
reward: -4.5873, last reward: -6.5072, gradient norm: 19.21: 19%|#9 | 121/625 [00:17<01:10, 7.12it/s]
reward: -4.5873, last reward: -6.5072, gradient norm: 19.21: 20%|#9 | 122/625 [00:17<01:10, 7.12it/s]
reward: -4.6548, last reward: -6.3766, gradient norm: 5.692: 20%|#9 | 122/625 [00:17<01:10, 7.12it/s]
reward: -4.6548, last reward: -6.3766, gradient norm: 5.692: 20%|#9 | 123/625 [00:17<01:10, 7.10it/s]
reward: -4.5134, last reward: -7.1955, gradient norm: 11.11: 20%|#9 | 123/625 [00:17<01:10, 7.10it/s]
reward: -4.5134, last reward: -7.1955, gradient norm: 11.11: 20%|#9 | 124/625 [00:17<01:10, 7.09it/s]
reward: -4.2481, last reward: -7.0591, gradient norm: 11.85: 20%|#9 | 124/625 [00:17<01:10, 7.09it/s]
reward: -4.2481, last reward: -7.0591, gradient norm: 11.85: 20%|## | 125/625 [00:17<01:10, 7.09it/s]
reward: -4.4500, last reward: -5.3368, gradient norm: 10.19: 20%|## | 125/625 [00:17<01:10, 7.09it/s]
reward: -4.4500, last reward: -5.3368, gradient norm: 10.19: 20%|## | 126/625 [00:17<01:10, 7.12it/s]
reward: -3.9708, last reward: -2.7059, gradient norm: 42.81: 20%|## | 126/625 [00:17<01:10, 7.12it/s]
reward: -3.9708, last reward: -2.7059, gradient norm: 42.81: 20%|## | 127/625 [00:17<01:09, 7.12it/s]
reward: -4.3031, last reward: -3.2534, gradient norm: 4.843: 20%|## | 127/625 [00:17<01:09, 7.12it/s]
reward: -4.3031, last reward: -3.2534, gradient norm: 4.843: 20%|## | 128/625 [00:17<01:09, 7.14it/s]
reward: -4.3327, last reward: -4.6193, gradient norm: 20.96: 20%|## | 128/625 [00:18<01:09, 7.14it/s]
reward: -4.3327, last reward: -4.6193, gradient norm: 20.96: 21%|## | 129/625 [00:18<01:09, 7.14it/s]
reward: -4.4831, last reward: -4.1172, gradient norm: 24.81: 21%|## | 129/625 [00:18<01:09, 7.14it/s]
reward: -4.4831, last reward: -4.1172, gradient norm: 24.81: 21%|## | 130/625 [00:18<01:09, 7.14it/s]
reward: -4.2593, last reward: -4.4219, gradient norm: 5.962: 21%|## | 130/625 [00:18<01:09, 7.14it/s]
reward: -4.2593, last reward: -4.4219, gradient norm: 5.962: 21%|## | 131/625 [00:18<01:09, 7.13it/s]
reward: -4.4800, last reward: -3.8380, gradient norm: 2.899: 21%|## | 131/625 [00:18<01:09, 7.13it/s]
reward: -4.4800, last reward: -3.8380, gradient norm: 2.899: 21%|##1 | 132/625 [00:18<01:09, 7.14it/s]
reward: -4.2721, last reward: -4.9048, gradient norm: 7.166: 21%|##1 | 132/625 [00:18<01:09, 7.14it/s]
reward: -4.2721, last reward: -4.9048, gradient norm: 7.166: 21%|##1 | 133/625 [00:18<01:08, 7.15it/s]
reward: -4.2419, last reward: -4.5248, gradient norm: 25.93: 21%|##1 | 133/625 [00:18<01:08, 7.15it/s]
reward: -4.2419, last reward: -4.5248, gradient norm: 25.93: 21%|##1 | 134/625 [00:18<01:08, 7.15it/s]
reward: -4.2139, last reward: -4.4278, gradient norm: 20.26: 21%|##1 | 134/625 [00:18<01:08, 7.15it/s]
reward: -4.2139, last reward: -4.4278, gradient norm: 20.26: 22%|##1 | 135/625 [00:18<01:08, 7.16it/s]
reward: -4.0690, last reward: -2.5140, gradient norm: 22.5: 22%|##1 | 135/625 [00:18<01:08, 7.16it/s]
reward: -4.0690, last reward: -2.5140, gradient norm: 22.5: 22%|##1 | 136/625 [00:18<01:08, 7.12it/s]
reward: -4.1140, last reward: -3.7402, gradient norm: 11.11: 22%|##1 | 136/625 [00:19<01:08, 7.12it/s]
reward: -4.1140, last reward: -3.7402, gradient norm: 11.11: 22%|##1 | 137/625 [00:19<01:08, 7.11it/s]
reward: -4.5356, last reward: -5.1636, gradient norm: 400.1: 22%|##1 | 137/625 [00:19<01:08, 7.11it/s]
reward: -4.5356, last reward: -5.1636, gradient norm: 400.1: 22%|##2 | 138/625 [00:19<01:08, 7.09it/s]
reward: -5.0671, last reward: -5.8798, gradient norm: 13.34: 22%|##2 | 138/625 [00:19<01:08, 7.09it/s]
reward: -5.0671, last reward: -5.8798, gradient norm: 13.34: 22%|##2 | 139/625 [00:19<01:08, 7.10it/s]
reward: -4.8918, last reward: -6.3298, gradient norm: 7.307: 22%|##2 | 139/625 [00:19<01:08, 7.10it/s]
reward: -4.8918, last reward: -6.3298, gradient norm: 7.307: 22%|##2 | 140/625 [00:19<01:07, 7.13it/s]
reward: -5.1779, last reward: -4.1915, gradient norm: 11.43: 22%|##2 | 140/625 [00:19<01:07, 7.13it/s]
reward: -5.1779, last reward: -4.1915, gradient norm: 11.43: 23%|##2 | 141/625 [00:19<01:07, 7.12it/s]
reward: -5.1771, last reward: -4.3624, gradient norm: 6.936: 23%|##2 | 141/625 [00:19<01:07, 7.12it/s]
reward: -5.1771, last reward: -4.3624, gradient norm: 6.936: 23%|##2 | 142/625 [00:19<01:07, 7.14it/s]
reward: -5.1683, last reward: -3.4810, gradient norm: 13.29: 23%|##2 | 142/625 [00:19<01:07, 7.14it/s]
reward: -5.1683, last reward: -3.4810, gradient norm: 13.29: 23%|##2 | 143/625 [00:19<01:07, 7.15it/s]
reward: -4.9373, last reward: -5.4435, gradient norm: 19.33: 23%|##2 | 143/625 [00:20<01:07, 7.15it/s]
reward: -4.9373, last reward: -5.4435, gradient norm: 19.33: 23%|##3 | 144/625 [00:20<01:07, 7.15it/s]
reward: -4.4396, last reward: -4.8092, gradient norm: 118.9: 23%|##3 | 144/625 [00:20<01:07, 7.15it/s]
reward: -4.4396, last reward: -4.8092, gradient norm: 118.9: 23%|##3 | 145/625 [00:20<01:07, 7.16it/s]
reward: -4.3911, last reward: -8.2572, gradient norm: 15.04: 23%|##3 | 145/625 [00:20<01:07, 7.16it/s]
reward: -4.3911, last reward: -8.2572, gradient norm: 15.04: 23%|##3 | 146/625 [00:20<01:06, 7.15it/s]
reward: -4.4212, last reward: -3.0260, gradient norm: 26.01: 23%|##3 | 146/625 [00:20<01:06, 7.15it/s]
reward: -4.4212, last reward: -3.0260, gradient norm: 26.01: 24%|##3 | 147/625 [00:20<01:06, 7.15it/s]
reward: -4.0939, last reward: -4.6478, gradient norm: 9.605: 24%|##3 | 147/625 [00:20<01:06, 7.15it/s]
reward: -4.0939, last reward: -4.6478, gradient norm: 9.605: 24%|##3 | 148/625 [00:20<01:06, 7.13it/s]
reward: -4.6606, last reward: -4.7289, gradient norm: 11.19: 24%|##3 | 148/625 [00:20<01:06, 7.13it/s]
reward: -4.6606, last reward: -4.7289, gradient norm: 11.19: 24%|##3 | 149/625 [00:20<01:06, 7.15it/s]
reward: -4.9300, last reward: -4.7193, gradient norm: 8.563: 24%|##3 | 149/625 [00:20<01:06, 7.15it/s]
reward: -4.9300, last reward: -4.7193, gradient norm: 8.563: 24%|##4 | 150/625 [00:20<01:06, 7.15it/s]
reward: -5.1166, last reward: -4.8514, gradient norm: 8.384: 24%|##4 | 150/625 [00:21<01:06, 7.15it/s]
reward: -5.1166, last reward: -4.8514, gradient norm: 8.384: 24%|##4 | 151/625 [00:21<01:06, 7.16it/s]
reward: -4.9108, last reward: -5.0672, gradient norm: 9.292: 24%|##4 | 151/625 [00:21<01:06, 7.16it/s]
reward: -4.9108, last reward: -5.0672, gradient norm: 9.292: 24%|##4 | 152/625 [00:21<01:06, 7.17it/s]
reward: -4.8591, last reward: -4.3768, gradient norm: 9.72: 24%|##4 | 152/625 [00:21<01:06, 7.17it/s]
reward: -4.8591, last reward: -4.3768, gradient norm: 9.72: 24%|##4 | 153/625 [00:21<01:05, 7.16it/s]
reward: -4.2721, last reward: -3.9976, gradient norm: 10.37: 24%|##4 | 153/625 [00:21<01:05, 7.16it/s]
reward: -4.2721, last reward: -3.9976, gradient norm: 10.37: 25%|##4 | 154/625 [00:21<01:05, 7.16it/s]
reward: -4.0576, last reward: -2.0067, gradient norm: 8.935: 25%|##4 | 154/625 [00:21<01:05, 7.16it/s]
reward: -4.0576, last reward: -2.0067, gradient norm: 8.935: 25%|##4 | 155/625 [00:21<01:05, 7.15it/s]
reward: -4.4199, last reward: -5.1722, gradient norm: 18.7: 25%|##4 | 155/625 [00:21<01:05, 7.15it/s]
reward: -4.4199, last reward: -5.1722, gradient norm: 18.7: 25%|##4 | 156/625 [00:21<01:05, 7.16it/s]
reward: -4.8310, last reward: -7.3466, gradient norm: 28.52: 25%|##4 | 156/625 [00:21<01:05, 7.16it/s]
reward: -4.8310, last reward: -7.3466, gradient norm: 28.52: 25%|##5 | 157/625 [00:21<01:05, 7.17it/s]
reward: -4.8631, last reward: -6.2492, gradient norm: 89.17: 25%|##5 | 157/625 [00:22<01:05, 7.17it/s]
reward: -4.8631, last reward: -6.2492, gradient norm: 89.17: 25%|##5 | 158/625 [00:22<01:05, 7.18it/s]
reward: -4.8763, last reward: -6.1277, gradient norm: 24.43: 25%|##5 | 158/625 [00:22<01:05, 7.18it/s]
reward: -4.8763, last reward: -6.1277, gradient norm: 24.43: 25%|##5 | 159/625 [00:22<01:04, 7.17it/s]
reward: -4.5562, last reward: -5.7446, gradient norm: 23.35: 25%|##5 | 159/625 [00:22<01:04, 7.17it/s]
reward: -4.5562, last reward: -5.7446, gradient norm: 23.35: 26%|##5 | 160/625 [00:22<01:04, 7.16it/s]
reward: -4.1082, last reward: -4.9830, gradient norm: 22.14: 26%|##5 | 160/625 [00:22<01:04, 7.16it/s]
reward: -4.1082, last reward: -4.9830, gradient norm: 22.14: 26%|##5 | 161/625 [00:22<01:04, 7.18it/s]
reward: -4.0946, last reward: -2.5229, gradient norm: 10.47: 26%|##5 | 161/625 [00:22<01:04, 7.18it/s]
reward: -4.0946, last reward: -2.5229, gradient norm: 10.47: 26%|##5 | 162/625 [00:22<01:04, 7.17it/s]
reward: -4.4574, last reward: -4.6900, gradient norm: 112.6: 26%|##5 | 162/625 [00:22<01:04, 7.17it/s]
reward: -4.4574, last reward: -4.6900, gradient norm: 112.6: 26%|##6 | 163/625 [00:22<01:04, 7.18it/s]
reward: -5.2229, last reward: -4.0318, gradient norm: 6.482: 26%|##6 | 163/625 [00:22<01:04, 7.18it/s]
reward: -5.2229, last reward: -4.0318, gradient norm: 6.482: 26%|##6 | 164/625 [00:22<01:04, 7.19it/s]
reward: -5.0543, last reward: -4.0817, gradient norm: 5.761: 26%|##6 | 164/625 [00:23<01:04, 7.19it/s]
reward: -5.0543, last reward: -4.0817, gradient norm: 5.761: 26%|##6 | 165/625 [00:23<01:04, 7.18it/s]
reward: -5.2809, last reward: -4.5118, gradient norm: 5.366: 26%|##6 | 165/625 [00:23<01:04, 7.18it/s]
reward: -5.2809, last reward: -4.5118, gradient norm: 5.366: 27%|##6 | 166/625 [00:23<01:04, 7.17it/s]
reward: -5.1142, last reward: -4.5635, gradient norm: 5.04: 27%|##6 | 166/625 [00:23<01:04, 7.17it/s]
reward: -5.1142, last reward: -4.5635, gradient norm: 5.04: 27%|##6 | 167/625 [00:23<01:03, 7.16it/s]
reward: -5.1949, last reward: -4.2327, gradient norm: 4.982: 27%|##6 | 167/625 [00:23<01:03, 7.16it/s]
reward: -5.1949, last reward: -4.2327, gradient norm: 4.982: 27%|##6 | 168/625 [00:23<01:03, 7.17it/s]
reward: -5.0967, last reward: -5.0387, gradient norm: 7.457: 27%|##6 | 168/625 [00:23<01:03, 7.17it/s]
reward: -5.0967, last reward: -5.0387, gradient norm: 7.457: 27%|##7 | 169/625 [00:23<01:03, 7.17it/s]
reward: -5.0782, last reward: -5.2150, gradient norm: 10.54: 27%|##7 | 169/625 [00:23<01:03, 7.17it/s]
reward: -5.0782, last reward: -5.2150, gradient norm: 10.54: 27%|##7 | 170/625 [00:23<01:03, 7.17it/s]
reward: -4.5222, last reward: -4.3725, gradient norm: 22.63: 27%|##7 | 170/625 [00:23<01:03, 7.17it/s]
reward: -4.5222, last reward: -4.3725, gradient norm: 22.63: 27%|##7 | 171/625 [00:23<01:03, 7.17it/s]
reward: -3.9288, last reward: -3.9837, gradient norm: 83.59: 27%|##7 | 171/625 [00:24<01:03, 7.17it/s]
reward: -3.9288, last reward: -3.9837, gradient norm: 83.59: 28%|##7 | 172/625 [00:24<01:03, 7.14it/s]
reward: -4.1416, last reward: -4.1099, gradient norm: 30.57: 28%|##7 | 172/625 [00:24<01:03, 7.14it/s]
reward: -4.1416, last reward: -4.1099, gradient norm: 30.57: 28%|##7 | 173/625 [00:24<01:03, 7.15it/s]
reward: -4.8620, last reward: -6.8475, gradient norm: 18.91: 28%|##7 | 173/625 [00:24<01:03, 7.15it/s]
reward: -4.8620, last reward: -6.8475, gradient norm: 18.91: 28%|##7 | 174/625 [00:24<01:03, 7.15it/s]
reward: -5.1807, last reward: -6.4375, gradient norm: 18.48: 28%|##7 | 174/625 [00:24<01:03, 7.15it/s]
reward: -5.1807, last reward: -6.4375, gradient norm: 18.48: 28%|##8 | 175/625 [00:24<01:02, 7.15it/s]
reward: -5.1148, last reward: -5.0645, gradient norm: 14.36: 28%|##8 | 175/625 [00:24<01:02, 7.15it/s]
reward: -5.1148, last reward: -5.0645, gradient norm: 14.36: 28%|##8 | 176/625 [00:24<01:02, 7.16it/s]
reward: -5.2751, last reward: -4.8313, gradient norm: 15.32: 28%|##8 | 176/625 [00:24<01:02, 7.16it/s]
reward: -5.2751, last reward: -4.8313, gradient norm: 15.32: 28%|##8 | 177/625 [00:24<01:02, 7.15it/s]
reward: -4.9286, last reward: -6.9770, gradient norm: 24.75: 28%|##8 | 177/625 [00:24<01:02, 7.15it/s]
reward: -4.9286, last reward: -6.9770, gradient norm: 24.75: 28%|##8 | 178/625 [00:24<01:02, 7.16it/s]
reward: -4.5735, last reward: -5.2837, gradient norm: 15.2: 28%|##8 | 178/625 [00:25<01:02, 7.16it/s]
reward: -4.5735, last reward: -5.2837, gradient norm: 15.2: 29%|##8 | 179/625 [00:25<01:02, 7.15it/s]
reward: -4.2926, last reward: -1.9489, gradient norm: 18.24: 29%|##8 | 179/625 [00:25<01:02, 7.15it/s]
reward: -4.2926, last reward: -1.9489, gradient norm: 18.24: 29%|##8 | 180/625 [00:25<01:02, 7.16it/s]
reward: -4.1507, last reward: -3.5593, gradient norm: 37.66: 29%|##8 | 180/625 [00:25<01:02, 7.16it/s]
reward: -4.1507, last reward: -3.5593, gradient norm: 37.66: 29%|##8 | 181/625 [00:25<01:02, 7.14it/s]
reward: -3.8724, last reward: -4.3567, gradient norm: 16.67: 29%|##8 | 181/625 [00:25<01:02, 7.14it/s]
reward: -3.8724, last reward: -4.3567, gradient norm: 16.67: 29%|##9 | 182/625 [00:25<01:02, 7.14it/s]
reward: -4.3574, last reward: -3.6140, gradient norm: 13.96: 29%|##9 | 182/625 [00:25<01:02, 7.14it/s]
reward: -4.3574, last reward: -3.6140, gradient norm: 13.96: 29%|##9 | 183/625 [00:25<01:01, 7.14it/s]
reward: -4.7895, last reward: -6.2518, gradient norm: 14.74: 29%|##9 | 183/625 [00:25<01:01, 7.14it/s]
reward: -4.7895, last reward: -6.2518, gradient norm: 14.74: 29%|##9 | 184/625 [00:25<01:01, 7.15it/s]
reward: -4.6146, last reward: -5.6969, gradient norm: 11.45: 29%|##9 | 184/625 [00:25<01:01, 7.15it/s]
reward: -4.6146, last reward: -5.6969, gradient norm: 11.45: 30%|##9 | 185/625 [00:25<01:01, 7.16it/s]
reward: -4.8776, last reward: -5.7358, gradient norm: 13.16: 30%|##9 | 185/625 [00:25<01:01, 7.16it/s]
reward: -4.8776, last reward: -5.7358, gradient norm: 13.16: 30%|##9 | 186/625 [00:25<01:01, 7.16it/s]
reward: -4.3722, last reward: -4.8428, gradient norm: 23.57: 30%|##9 | 186/625 [00:26<01:01, 7.16it/s]
reward: -4.3722, last reward: -4.8428, gradient norm: 23.57: 30%|##9 | 187/625 [00:26<01:01, 7.15it/s]
reward: -4.2656, last reward: -3.7955, gradient norm: 54.67: 30%|##9 | 187/625 [00:26<01:01, 7.15it/s]
reward: -4.2656, last reward: -3.7955, gradient norm: 54.67: 30%|### | 188/625 [00:26<01:01, 7.15it/s]
reward: -4.0092, last reward: -1.7106, gradient norm: 7.829: 30%|### | 188/625 [00:26<01:01, 7.15it/s]
reward: -4.0092, last reward: -1.7106, gradient norm: 7.829: 30%|### | 189/625 [00:26<01:00, 7.16it/s]
reward: -4.2264, last reward: -3.6919, gradient norm: 16.17: 30%|### | 189/625 [00:26<01:00, 7.16it/s]
reward: -4.2264, last reward: -3.6919, gradient norm: 16.17: 30%|### | 190/625 [00:26<01:00, 7.14it/s]
reward: -4.1438, last reward: -2.1362, gradient norm: 19.43: 30%|### | 190/625 [00:26<01:00, 7.14it/s]
reward: -4.1438, last reward: -2.1362, gradient norm: 19.43: 31%|### | 191/625 [00:26<01:00, 7.14it/s]
reward: -4.0618, last reward: -2.8217, gradient norm: 73.63: 31%|### | 191/625 [00:26<01:00, 7.14it/s]
reward: -4.0618, last reward: -2.8217, gradient norm: 73.63: 31%|### | 192/625 [00:26<01:00, 7.15it/s]
reward: -3.9420, last reward: -3.6765, gradient norm: 34.1: 31%|### | 192/625 [00:26<01:00, 7.15it/s]
reward: -3.9420, last reward: -3.6765, gradient norm: 34.1: 31%|### | 193/625 [00:26<01:00, 7.14it/s]
reward: -3.7745, last reward: -4.0709, gradient norm: 26.48: 31%|### | 193/625 [00:27<01:00, 7.14it/s]
reward: -3.7745, last reward: -4.0709, gradient norm: 26.48: 31%|###1 | 194/625 [00:27<01:00, 7.13it/s]
reward: -3.9478, last reward: -2.6867, gradient norm: 22.82: 31%|###1 | 194/625 [00:27<01:00, 7.13it/s]
reward: -3.9478, last reward: -2.6867, gradient norm: 22.82: 31%|###1 | 195/625 [00:27<01:00, 7.14it/s]
reward: -3.6507, last reward: -2.6225, gradient norm: 37.44: 31%|###1 | 195/625 [00:27<01:00, 7.14it/s]
reward: -3.6507, last reward: -2.6225, gradient norm: 37.44: 31%|###1 | 196/625 [00:27<00:59, 7.15it/s]
reward: -4.2244, last reward: -3.2195, gradient norm: 10.71: 31%|###1 | 196/625 [00:27<00:59, 7.15it/s]
reward: -4.2244, last reward: -3.2195, gradient norm: 10.71: 32%|###1 | 197/625 [00:27<00:59, 7.14it/s]
reward: -4.5385, last reward: -3.9263, gradient norm: 31.03: 32%|###1 | 197/625 [00:27<00:59, 7.14it/s]
reward: -4.5385, last reward: -3.9263, gradient norm: 31.03: 32%|###1 | 198/625 [00:27<00:59, 7.14it/s]
reward: -4.1878, last reward: -3.2374, gradient norm: 34.35: 32%|###1 | 198/625 [00:27<00:59, 7.14it/s]
reward: -4.1878, last reward: -3.2374, gradient norm: 34.35: 32%|###1 | 199/625 [00:27<00:59, 7.14it/s]
reward: -3.8054, last reward: -2.3504, gradient norm: 5.557: 32%|###1 | 199/625 [00:27<00:59, 7.14it/s]
reward: -3.8054, last reward: -2.3504, gradient norm: 5.557: 32%|###2 | 200/625 [00:27<00:59, 7.13it/s]
reward: -4.0766, last reward: -4.6825, gradient norm: 38.72: 32%|###2 | 200/625 [00:28<00:59, 7.13it/s]
reward: -4.0766, last reward: -4.6825, gradient norm: 38.72: 32%|###2 | 201/625 [00:28<00:59, 7.14it/s]
reward: -4.2011, last reward: -5.8393, gradient norm: 21.06: 32%|###2 | 201/625 [00:28<00:59, 7.14it/s]
reward: -4.2011, last reward: -5.8393, gradient norm: 21.06: 32%|###2 | 202/625 [00:28<00:59, 7.14it/s]
reward: -4.0803, last reward: -3.7815, gradient norm: 10.6: 32%|###2 | 202/625 [00:28<00:59, 7.14it/s]
reward: -4.0803, last reward: -3.7815, gradient norm: 10.6: 32%|###2 | 203/625 [00:28<00:59, 7.14it/s]
reward: -3.8363, last reward: -3.2460, gradient norm: 32.57: 32%|###2 | 203/625 [00:28<00:59, 7.14it/s]
reward: -3.8363, last reward: -3.2460, gradient norm: 32.57: 33%|###2 | 204/625 [00:28<00:58, 7.15it/s]
reward: -3.8643, last reward: -3.2191, gradient norm: 8.593: 33%|###2 | 204/625 [00:28<00:58, 7.15it/s]
reward: -3.8643, last reward: -3.2191, gradient norm: 8.593: 33%|###2 | 205/625 [00:28<00:58, 7.17it/s]
reward: -4.0773, last reward: -5.1343, gradient norm: 14.49: 33%|###2 | 205/625 [00:28<00:58, 7.17it/s]
reward: -4.0773, last reward: -5.1343, gradient norm: 14.49: 33%|###2 | 206/625 [00:28<00:58, 7.17it/s]
reward: -4.1400, last reward: -5.8657, gradient norm: 17.05: 33%|###2 | 206/625 [00:28<00:58, 7.17it/s]
reward: -4.1400, last reward: -5.8657, gradient norm: 17.05: 33%|###3 | 207/625 [00:28<00:58, 7.17it/s]
reward: -3.9304, last reward: -2.7584, gradient norm: 33.25: 33%|###3 | 207/625 [00:29<00:58, 7.17it/s]
reward: -3.9304, last reward: -2.7584, gradient norm: 33.25: 33%|###3 | 208/625 [00:29<00:58, 7.17it/s]
reward: -3.8752, last reward: -4.2307, gradient norm: 10.76: 33%|###3 | 208/625 [00:29<00:58, 7.17it/s]
reward: -3.8752, last reward: -4.2307, gradient norm: 10.76: 33%|###3 | 209/625 [00:29<00:58, 7.17it/s]
reward: -3.5250, last reward: -1.4869, gradient norm: 40.8: 33%|###3 | 209/625 [00:29<00:58, 7.17it/s]
reward: -3.5250, last reward: -1.4869, gradient norm: 40.8: 34%|###3 | 210/625 [00:29<00:57, 7.18it/s]
reward: -3.7837, last reward: -2.5762, gradient norm: 193.3: 34%|###3 | 210/625 [00:29<00:57, 7.18it/s]
reward: -3.7837, last reward: -2.5762, gradient norm: 193.3: 34%|###3 | 211/625 [00:29<00:57, 7.18it/s]
reward: -3.6661, last reward: -1.8600, gradient norm: 136.5: 34%|###3 | 211/625 [00:29<00:57, 7.18it/s]
reward: -3.6661, last reward: -1.8600, gradient norm: 136.5: 34%|###3 | 212/625 [00:29<00:57, 7.18it/s]
reward: -4.2502, last reward: -3.1752, gradient norm: 21.44: 34%|###3 | 212/625 [00:29<00:57, 7.18it/s]
reward: -4.2502, last reward: -3.1752, gradient norm: 21.44: 34%|###4 | 213/625 [00:29<00:57, 7.17it/s]
reward: -4.3075, last reward: -2.8871, gradient norm: 30.65: 34%|###4 | 213/625 [00:29<00:57, 7.17it/s]
reward: -4.3075, last reward: -2.8871, gradient norm: 30.65: 34%|###4 | 214/625 [00:29<00:57, 7.17it/s]
reward: -3.9406, last reward: -2.8090, gradient norm: 20.18: 34%|###4 | 214/625 [00:30<00:57, 7.17it/s]
reward: -3.9406, last reward: -2.8090, gradient norm: 20.18: 34%|###4 | 215/625 [00:30<00:57, 7.17it/s]
reward: -3.6291, last reward: -2.8923, gradient norm: 7.876: 34%|###4 | 215/625 [00:30<00:57, 7.17it/s]
reward: -3.6291, last reward: -2.8923, gradient norm: 7.876: 35%|###4 | 216/625 [00:30<00:57, 7.17it/s]
reward: -3.5112, last reward: -3.9504, gradient norm: 3.21e+03: 35%|###4 | 216/625 [00:30<00:57, 7.17it/s]
reward: -3.5112, last reward: -3.9504, gradient norm: 3.21e+03: 35%|###4 | 217/625 [00:30<00:56, 7.18it/s]
reward: -3.7431, last reward: -2.7880, gradient norm: 13.73: 35%|###4 | 217/625 [00:30<00:56, 7.18it/s]
reward: -3.7431, last reward: -2.7880, gradient norm: 13.73: 35%|###4 | 218/625 [00:30<00:56, 7.17it/s]
reward: -3.4463, last reward: -4.5432, gradient norm: 32.37: 35%|###4 | 218/625 [00:30<00:56, 7.17it/s]
reward: -3.4463, last reward: -4.5432, gradient norm: 32.37: 35%|###5 | 219/625 [00:30<00:56, 7.17it/s]
reward: -3.3793, last reward: -3.3313, gradient norm: 60.63: 35%|###5 | 219/625 [00:30<00:56, 7.17it/s]
reward: -3.3793, last reward: -3.3313, gradient norm: 60.63: 35%|###5 | 220/625 [00:30<00:56, 7.17it/s]
reward: -3.8843, last reward: -3.0369, gradient norm: 5.065: 35%|###5 | 220/625 [00:30<00:56, 7.17it/s]
reward: -3.8843, last reward: -3.0369, gradient norm: 5.065: 35%|###5 | 221/625 [00:30<00:56, 7.16it/s]
reward: -3.4828, last reward: -3.8391, gradient norm: 59.85: 35%|###5 | 221/625 [00:31<00:56, 7.16it/s]
reward: -3.4828, last reward: -3.8391, gradient norm: 59.85: 36%|###5 | 222/625 [00:31<00:56, 7.14it/s]
reward: -3.6265, last reward: -4.2913, gradient norm: 8.947: 36%|###5 | 222/625 [00:31<00:56, 7.14it/s]
reward: -3.6265, last reward: -4.2913, gradient norm: 8.947: 36%|###5 | 223/625 [00:31<00:56, 7.16it/s]
reward: -3.5541, last reward: -4.1252, gradient norm: 255.9: 36%|###5 | 223/625 [00:31<00:56, 7.16it/s]
reward: -3.5541, last reward: -4.1252, gradient norm: 255.9: 36%|###5 | 224/625 [00:31<00:56, 7.14it/s]
reward: -3.7342, last reward: -2.2396, gradient norm: 7.995: 36%|###5 | 224/625 [00:31<00:56, 7.14it/s]
reward: -3.7342, last reward: -2.2396, gradient norm: 7.995: 36%|###6 | 225/625 [00:31<00:55, 7.15it/s]
reward: -3.5936, last reward: -4.1924, gradient norm: 59.49: 36%|###6 | 225/625 [00:31<00:55, 7.15it/s]
reward: -3.5936, last reward: -4.1924, gradient norm: 59.49: 36%|###6 | 226/625 [00:31<00:55, 7.16it/s]
reward: -3.9975, last reward: -4.2045, gradient norm: 21.77: 36%|###6 | 226/625 [00:31<00:55, 7.16it/s]
reward: -3.9975, last reward: -4.2045, gradient norm: 21.77: 36%|###6 | 227/625 [00:31<00:55, 7.15it/s]
reward: -3.8367, last reward: -1.9540, gradient norm: 32.26: 36%|###6 | 227/625 [00:31<00:55, 7.15it/s]
reward: -3.8367, last reward: -1.9540, gradient norm: 32.26: 36%|###6 | 228/625 [00:31<00:55, 7.16it/s]
reward: -3.7259, last reward: -3.6743, gradient norm: 28.62: 36%|###6 | 228/625 [00:31<00:55, 7.16it/s]
reward: -3.7259, last reward: -3.6743, gradient norm: 28.62: 37%|###6 | 229/625 [00:31<00:55, 7.14it/s]
reward: -3.4827, last reward: -3.7528, gradient norm: 64.85: 37%|###6 | 229/625 [00:32<00:55, 7.14it/s]
reward: -3.4827, last reward: -3.7528, gradient norm: 64.85: 37%|###6 | 230/625 [00:32<00:55, 7.16it/s]
reward: -3.7361, last reward: -3.8756, gradient norm: 24.69: 37%|###6 | 230/625 [00:32<00:55, 7.16it/s]
reward: -3.7361, last reward: -3.8756, gradient norm: 24.69: 37%|###6 | 231/625 [00:32<00:54, 7.17it/s]
reward: -3.7646, last reward: -3.1116, gradient norm: 14.25: 37%|###6 | 231/625 [00:32<00:54, 7.17it/s]
reward: -3.7646, last reward: -3.1116, gradient norm: 14.25: 37%|###7 | 232/625 [00:32<00:54, 7.17it/s]
reward: -3.5426, last reward: -2.8385, gradient norm: 34.07: 37%|###7 | 232/625 [00:32<00:54, 7.17it/s]
reward: -3.5426, last reward: -2.8385, gradient norm: 34.07: 37%|###7 | 233/625 [00:32<00:54, 7.15it/s]
reward: -3.5662, last reward: -1.8585, gradient norm: 11.26: 37%|###7 | 233/625 [00:32<00:54, 7.15it/s]
reward: -3.5662, last reward: -1.8585, gradient norm: 11.26: 37%|###7 | 234/625 [00:32<00:54, 7.15it/s]
reward: -3.8234, last reward: -2.7930, gradient norm: 32.18: 37%|###7 | 234/625 [00:32<00:54, 7.15it/s]
reward: -3.8234, last reward: -2.7930, gradient norm: 32.18: 38%|###7 | 235/625 [00:32<00:54, 7.15it/s]
reward: -4.2648, last reward: -4.9309, gradient norm: 24.83: 38%|###7 | 235/625 [00:32<00:54, 7.15it/s]
reward: -4.2648, last reward: -4.9309, gradient norm: 24.83: 38%|###7 | 236/625 [00:32<00:54, 7.14it/s]
reward: -4.2039, last reward: -3.6817, gradient norm: 19.24: 38%|###7 | 236/625 [00:33<00:54, 7.14it/s]
reward: -4.2039, last reward: -3.6817, gradient norm: 19.24: 38%|###7 | 237/625 [00:33<00:54, 7.15it/s]
reward: -4.0943, last reward: -3.1533, gradient norm: 145.1: 38%|###7 | 237/625 [00:33<00:54, 7.15it/s]
reward: -4.0943, last reward: -3.1533, gradient norm: 145.1: 38%|###8 | 238/625 [00:33<00:54, 7.16it/s]
reward: -4.3045, last reward: -3.0483, gradient norm: 20.89: 38%|###8 | 238/625 [00:33<00:54, 7.16it/s]
reward: -4.3045, last reward: -3.0483, gradient norm: 20.89: 38%|###8 | 239/625 [00:33<00:53, 7.17it/s]
reward: -4.4128, last reward: -5.2528, gradient norm: 24.97: 38%|###8 | 239/625 [00:33<00:53, 7.17it/s]
reward: -4.4128, last reward: -5.2528, gradient norm: 24.97: 38%|###8 | 240/625 [00:33<00:53, 7.17it/s]
reward: -4.6415, last reward: -8.0201, gradient norm: 26.74: 38%|###8 | 240/625 [00:33<00:53, 7.17it/s]
reward: -4.6415, last reward: -8.0201, gradient norm: 26.74: 39%|###8 | 241/625 [00:33<00:53, 7.16it/s]
reward: -4.4437, last reward: -5.4365, gradient norm: 132.7: 39%|###8 | 241/625 [00:33<00:53, 7.16it/s]
reward: -4.4437, last reward: -5.4365, gradient norm: 132.7: 39%|###8 | 242/625 [00:33<00:53, 7.16it/s]
reward: -4.0358, last reward: -3.4943, gradient norm: 11.46: 39%|###8 | 242/625 [00:33<00:53, 7.16it/s]
reward: -4.0358, last reward: -3.4943, gradient norm: 11.46: 39%|###8 | 243/625 [00:33<00:53, 7.17it/s]
reward: -4.1272, last reward: -3.5003, gradient norm: 68.09: 39%|###8 | 243/625 [00:34<00:53, 7.17it/s]
reward: -4.1272, last reward: -3.5003, gradient norm: 68.09: 39%|###9 | 244/625 [00:34<00:53, 7.16it/s]
reward: -4.1180, last reward: -4.2637, gradient norm: 39.25: 39%|###9 | 244/625 [00:34<00:53, 7.16it/s]
reward: -4.1180, last reward: -4.2637, gradient norm: 39.25: 39%|###9 | 245/625 [00:34<00:53, 7.14it/s]
reward: -4.7197, last reward: -3.0873, gradient norm: 12.2: 39%|###9 | 245/625 [00:34<00:53, 7.14it/s]
reward: -4.7197, last reward: -3.0873, gradient norm: 12.2: 39%|###9 | 246/625 [00:34<00:53, 7.14it/s]
reward: -4.2917, last reward: -3.6656, gradient norm: 17.17: 39%|###9 | 246/625 [00:34<00:53, 7.14it/s]
reward: -4.2917, last reward: -3.6656, gradient norm: 17.17: 40%|###9 | 247/625 [00:34<00:52, 7.14it/s]
reward: -4.0160, last reward: -3.0738, gradient norm: 43.07: 40%|###9 | 247/625 [00:34<00:52, 7.14it/s]
reward: -4.0160, last reward: -3.0738, gradient norm: 43.07: 40%|###9 | 248/625 [00:34<00:52, 7.14it/s]
reward: -4.3689, last reward: -4.0120, gradient norm: 11.81: 40%|###9 | 248/625 [00:34<00:52, 7.14it/s]
reward: -4.3689, last reward: -4.0120, gradient norm: 11.81: 40%|###9 | 249/625 [00:34<00:52, 7.14it/s]
reward: -4.5570, last reward: -7.0475, gradient norm: 22.45: 40%|###9 | 249/625 [00:34<00:52, 7.14it/s]
reward: -4.5570, last reward: -7.0475, gradient norm: 22.45: 40%|#### | 250/625 [00:34<00:52, 7.15it/s]
reward: -4.4423, last reward: -5.2220, gradient norm: 18.4: 40%|#### | 250/625 [00:35<00:52, 7.15it/s]
reward: -4.4423, last reward: -5.2220, gradient norm: 18.4: 40%|#### | 251/625 [00:35<00:52, 7.13it/s]
reward: -4.2118, last reward: -4.6803, gradient norm: 15.86: 40%|#### | 251/625 [00:35<00:52, 7.13it/s]
reward: -4.2118, last reward: -4.6803, gradient norm: 15.86: 40%|#### | 252/625 [00:35<00:52, 7.15it/s]
reward: -4.1465, last reward: -3.7214, gradient norm: 25.93: 40%|#### | 252/625 [00:35<00:52, 7.15it/s]
reward: -4.1465, last reward: -3.7214, gradient norm: 25.93: 40%|#### | 253/625 [00:35<00:51, 7.16it/s]
reward: -3.8801, last reward: -2.7034, gradient norm: 103.6: 40%|#### | 253/625 [00:35<00:51, 7.16it/s]
reward: -3.8801, last reward: -2.7034, gradient norm: 103.6: 41%|#### | 254/625 [00:35<00:51, 7.15it/s]
reward: -3.9136, last reward: -4.4076, gradient norm: 17.63: 41%|#### | 254/625 [00:35<00:51, 7.15it/s]
reward: -3.9136, last reward: -4.4076, gradient norm: 17.63: 41%|#### | 255/625 [00:35<00:51, 7.15it/s]
reward: -3.7589, last reward: -4.5013, gradient norm: 143.3: 41%|#### | 255/625 [00:35<00:51, 7.15it/s]
reward: -3.7589, last reward: -4.5013, gradient norm: 143.3: 41%|#### | 256/625 [00:35<00:51, 7.15it/s]
reward: -3.8150, last reward: -3.2241, gradient norm: 113.9: 41%|#### | 256/625 [00:35<00:51, 7.15it/s]
reward: -3.8150, last reward: -3.2241, gradient norm: 113.9: 41%|####1 | 257/625 [00:35<00:51, 7.16it/s]
reward: -4.0753, last reward: -3.8081, gradient norm: 14.8: 41%|####1 | 257/625 [00:36<00:51, 7.16it/s]
reward: -4.0753, last reward: -3.8081, gradient norm: 14.8: 41%|####1 | 258/625 [00:36<00:51, 7.17it/s]
reward: -4.1951, last reward: -4.8314, gradient norm: 27.63: 41%|####1 | 258/625 [00:36<00:51, 7.17it/s]
reward: -4.1951, last reward: -4.8314, gradient norm: 27.63: 41%|####1 | 259/625 [00:36<00:51, 7.16it/s]
reward: -4.0038, last reward: -2.5333, gradient norm: 42.85: 41%|####1 | 259/625 [00:36<00:51, 7.16it/s]
reward: -4.0038, last reward: -2.5333, gradient norm: 42.85: 42%|####1 | 260/625 [00:36<00:50, 7.17it/s]
reward: -4.0889, last reward: -2.4616, gradient norm: 13.78: 42%|####1 | 260/625 [00:36<00:50, 7.17it/s]
reward: -4.0889, last reward: -2.4616, gradient norm: 13.78: 42%|####1 | 261/625 [00:36<00:50, 7.17it/s]
reward: -4.0655, last reward: -2.6873, gradient norm: 10.98: 42%|####1 | 261/625 [00:36<00:50, 7.17it/s]
reward: -4.0655, last reward: -2.6873, gradient norm: 10.98: 42%|####1 | 262/625 [00:36<00:50, 7.18it/s]
reward: -3.8333, last reward: -1.9476, gradient norm: 13.47: 42%|####1 | 262/625 [00:36<00:50, 7.18it/s]
reward: -3.8333, last reward: -1.9476, gradient norm: 13.47: 42%|####2 | 263/625 [00:36<00:50, 7.17it/s]
reward: -3.7554, last reward: -4.3798, gradient norm: 41.76: 42%|####2 | 263/625 [00:36<00:50, 7.17it/s]
reward: -3.7554, last reward: -4.3798, gradient norm: 41.76: 42%|####2 | 264/625 [00:36<00:50, 7.17it/s]
reward: -3.3717, last reward: -2.3947, gradient norm: 6.529: 42%|####2 | 264/625 [00:37<00:50, 7.17it/s]
reward: -3.3717, last reward: -2.3947, gradient norm: 6.529: 42%|####2 | 265/625 [00:37<00:50, 7.18it/s]
reward: -4.3060, last reward: -4.6495, gradient norm: 11.24: 42%|####2 | 265/625 [00:37<00:50, 7.18it/s]
reward: -4.3060, last reward: -4.6495, gradient norm: 11.24: 43%|####2 | 266/625 [00:37<00:49, 7.19it/s]
reward: -4.7467, last reward: -5.8889, gradient norm: 12.35: 43%|####2 | 266/625 [00:37<00:49, 7.19it/s]
reward: -4.7467, last reward: -5.8889, gradient norm: 12.35: 43%|####2 | 267/625 [00:37<00:49, 7.19it/s]
reward: -4.9281, last reward: -4.8457, gradient norm: 6.591: 43%|####2 | 267/625 [00:37<00:49, 7.19it/s]
reward: -4.9281, last reward: -4.8457, gradient norm: 6.591: 43%|####2 | 268/625 [00:37<00:49, 7.19it/s]
reward: -4.7137, last reward: -4.0536, gradient norm: 5.771: 43%|####2 | 268/625 [00:37<00:49, 7.19it/s]
reward: -4.7137, last reward: -4.0536, gradient norm: 5.771: 43%|####3 | 269/625 [00:37<00:49, 7.19it/s]
reward: -4.7197, last reward: -4.1651, gradient norm: 5.388: 43%|####3 | 269/625 [00:37<00:49, 7.19it/s]
reward: -4.7197, last reward: -4.1651, gradient norm: 5.388: 43%|####3 | 270/625 [00:37<00:49, 7.18it/s]
reward: -4.8246, last reward: -5.5709, gradient norm: 8.281: 43%|####3 | 270/625 [00:37<00:49, 7.18it/s]
reward: -4.8246, last reward: -5.5709, gradient norm: 8.281: 43%|####3 | 271/625 [00:37<00:49, 7.19it/s]
reward: -4.7502, last reward: -5.0521, gradient norm: 9.032: 43%|####3 | 271/625 [00:37<00:49, 7.19it/s]
reward: -4.7502, last reward: -5.0521, gradient norm: 9.032: 44%|####3 | 272/625 [00:37<00:49, 7.20it/s]
reward: -4.5475, last reward: -4.7253, gradient norm: 21.18: 44%|####3 | 272/625 [00:38<00:49, 7.20it/s]
reward: -4.5475, last reward: -4.7253, gradient norm: 21.18: 44%|####3 | 273/625 [00:38<00:48, 7.21it/s]
reward: -4.2856, last reward: -3.7130, gradient norm: 13.53: 44%|####3 | 273/625 [00:38<00:48, 7.21it/s]
reward: -4.2856, last reward: -3.7130, gradient norm: 13.53: 44%|####3 | 274/625 [00:38<00:48, 7.19it/s]
reward: -3.2778, last reward: -3.4122, gradient norm: 28.52: 44%|####3 | 274/625 [00:38<00:48, 7.19it/s]
reward: -3.2778, last reward: -3.4122, gradient norm: 28.52: 44%|####4 | 275/625 [00:38<00:48, 7.19it/s]
reward: -3.8368, last reward: -2.1841, gradient norm: 2.07: 44%|####4 | 275/625 [00:38<00:48, 7.19it/s]
reward: -3.8368, last reward: -2.1841, gradient norm: 2.07: 44%|####4 | 276/625 [00:38<00:48, 7.19it/s]
reward: -3.9622, last reward: -3.1603, gradient norm: 1.003e+03: 44%|####4 | 276/625 [00:38<00:48, 7.19it/s]
reward: -3.9622, last reward: -3.1603, gradient norm: 1.003e+03: 44%|####4 | 277/625 [00:38<00:48, 7.19it/s]
reward: -4.0247, last reward: -2.9830, gradient norm: 8.346: 44%|####4 | 277/625 [00:38<00:48, 7.19it/s]
reward: -4.0247, last reward: -2.9830, gradient norm: 8.346: 44%|####4 | 278/625 [00:38<00:48, 7.20it/s]
reward: -4.2238, last reward: -4.6418, gradient norm: 14.55: 44%|####4 | 278/625 [00:38<00:48, 7.20it/s]
reward: -4.2238, last reward: -4.6418, gradient norm: 14.55: 45%|####4 | 279/625 [00:38<00:48, 7.19it/s]
reward: -4.0626, last reward: -4.2538, gradient norm: 17.88: 45%|####4 | 279/625 [00:39<00:48, 7.19it/s]
reward: -4.0626, last reward: -4.2538, gradient norm: 17.88: 45%|####4 | 280/625 [00:39<00:47, 7.19it/s]
reward: -4.0149, last reward: -3.7380, gradient norm: 13.13: 45%|####4 | 280/625 [00:39<00:47, 7.19it/s]
reward: -4.0149, last reward: -3.7380, gradient norm: 13.13: 45%|####4 | 281/625 [00:39<00:47, 7.20it/s]
reward: -4.2167, last reward: -2.8911, gradient norm: 11.41: 45%|####4 | 281/625 [00:39<00:47, 7.20it/s]
reward: -4.2167, last reward: -2.8911, gradient norm: 11.41: 45%|####5 | 282/625 [00:39<00:47, 7.19it/s]
reward: -3.8725, last reward: -4.1983, gradient norm: 18.88: 45%|####5 | 282/625 [00:39<00:47, 7.19it/s]
reward: -3.8725, last reward: -4.1983, gradient norm: 18.88: 45%|####5 | 283/625 [00:39<00:47, 7.19it/s]
reward: -2.8142, last reward: -2.3709, gradient norm: 43.73: 45%|####5 | 283/625 [00:39<00:47, 7.19it/s]
reward: -2.8142, last reward: -2.3709, gradient norm: 43.73: 45%|####5 | 284/625 [00:39<00:47, 7.19it/s]
reward: -3.2022, last reward: -2.4989, gradient norm: 11.14: 45%|####5 | 284/625 [00:39<00:47, 7.19it/s]
reward: -3.2022, last reward: -2.4989, gradient norm: 11.14: 46%|####5 | 285/625 [00:39<00:47, 7.20it/s]
reward: -3.6464, last reward: -1.6210, gradient norm: 43.37: 46%|####5 | 285/625 [00:39<00:47, 7.20it/s]
reward: -3.6464, last reward: -1.6210, gradient norm: 43.37: 46%|####5 | 286/625 [00:39<00:47, 7.19it/s]
reward: -3.9726, last reward: -3.0820, gradient norm: 39.93: 46%|####5 | 286/625 [00:40<00:47, 7.19it/s]
reward: -3.9726, last reward: -3.0820, gradient norm: 39.93: 46%|####5 | 287/625 [00:40<00:46, 7.19it/s]
reward: -3.6975, last reward: -2.9091, gradient norm: 29.46: 46%|####5 | 287/625 [00:40<00:46, 7.19it/s]
reward: -3.6975, last reward: -2.9091, gradient norm: 29.46: 46%|####6 | 288/625 [00:40<00:46, 7.19it/s]
reward: -3.4926, last reward: -2.4791, gradient norm: 160.7: 46%|####6 | 288/625 [00:40<00:46, 7.19it/s]
reward: -3.4926, last reward: -2.4791, gradient norm: 160.7: 46%|####6 | 289/625 [00:40<00:46, 7.20it/s]
reward: -3.0905, last reward: -1.3500, gradient norm: 31.38: 46%|####6 | 289/625 [00:40<00:46, 7.20it/s]
reward: -3.0905, last reward: -1.3500, gradient norm: 31.38: 46%|####6 | 290/625 [00:40<00:46, 7.19it/s]
reward: -3.2287, last reward: -2.7137, gradient norm: 26.31: 46%|####6 | 290/625 [00:40<00:46, 7.19it/s]
reward: -3.2287, last reward: -2.7137, gradient norm: 26.31: 47%|####6 | 291/625 [00:40<00:46, 7.18it/s]
reward: -2.9918, last reward: -1.5543, gradient norm: 29.73: 47%|####6 | 291/625 [00:40<00:46, 7.18it/s]
reward: -2.9918, last reward: -1.5543, gradient norm: 29.73: 47%|####6 | 292/625 [00:40<00:46, 7.16it/s]
reward: -2.9245, last reward: -0.6444, gradient norm: 2.631: 47%|####6 | 292/625 [00:40<00:46, 7.16it/s]
reward: -2.9245, last reward: -0.6444, gradient norm: 2.631: 47%|####6 | 293/625 [00:40<00:46, 7.13it/s]
reward: -3.0448, last reward: -0.4769, gradient norm: 7.266: 47%|####6 | 293/625 [00:41<00:46, 7.13it/s]
reward: -3.0448, last reward: -0.4769, gradient norm: 7.266: 47%|####7 | 294/625 [00:41<00:46, 7.10it/s]
reward: -2.8566, last reward: -1.7208, gradient norm: 25.22: 47%|####7 | 294/625 [00:41<00:46, 7.10it/s]
reward: -2.8566, last reward: -1.7208, gradient norm: 25.22: 47%|####7 | 295/625 [00:41<00:46, 7.10it/s]
reward: -2.8872, last reward: -1.0966, gradient norm: 8.247: 47%|####7 | 295/625 [00:41<00:46, 7.10it/s]
reward: -2.8872, last reward: -1.0966, gradient norm: 8.247: 47%|####7 | 296/625 [00:41<00:46, 7.10it/s]
reward: -2.5303, last reward: -0.1537, gradient norm: 2.023: 47%|####7 | 296/625 [00:41<00:46, 7.10it/s]
reward: -2.5303, last reward: -0.1537, gradient norm: 2.023: 48%|####7 | 297/625 [00:41<00:46, 7.11it/s]
reward: -2.6817, last reward: -0.2682, gradient norm: 7.564: 48%|####7 | 297/625 [00:41<00:46, 7.11it/s]
reward: -2.6817, last reward: -0.2682, gradient norm: 7.564: 48%|####7 | 298/625 [00:41<00:45, 7.13it/s]
reward: -2.4318, last reward: -0.5063, gradient norm: 14.87: 48%|####7 | 298/625 [00:41<00:45, 7.13it/s]
reward: -2.4318, last reward: -0.5063, gradient norm: 14.87: 48%|####7 | 299/625 [00:41<00:45, 7.11it/s]
reward: -2.7475, last reward: -1.4190, gradient norm: 21.66: 48%|####7 | 299/625 [00:41<00:45, 7.11it/s]
reward: -2.7475, last reward: -1.4190, gradient norm: 21.66: 48%|####8 | 300/625 [00:41<00:45, 7.11it/s]
reward: -2.8186, last reward: -2.5077, gradient norm: 22.4: 48%|####8 | 300/625 [00:42<00:45, 7.11it/s]
reward: -2.8186, last reward: -2.5077, gradient norm: 22.4: 48%|####8 | 301/625 [00:42<00:45, 7.07it/s]
reward: -3.1883, last reward: -1.5291, gradient norm: 7.472: 48%|####8 | 301/625 [00:42<00:45, 7.07it/s]
reward: -3.1883, last reward: -1.5291, gradient norm: 7.472: 48%|####8 | 302/625 [00:42<00:45, 7.06it/s]
reward: -2.1256, last reward: -0.3998, gradient norm: 11.01: 48%|####8 | 302/625 [00:42<00:45, 7.06it/s]
reward: -2.1256, last reward: -0.3998, gradient norm: 11.01: 48%|####8 | 303/625 [00:42<00:45, 7.07it/s]
reward: -2.3622, last reward: -0.0930, gradient norm: 1.626: 48%|####8 | 303/625 [00:42<00:45, 7.07it/s]
reward: -2.3622, last reward: -0.0930, gradient norm: 1.626: 49%|####8 | 304/625 [00:42<00:45, 7.05it/s]
reward: -1.9500, last reward: -0.0075, gradient norm: 0.5664: 49%|####8 | 304/625 [00:42<00:45, 7.05it/s]
reward: -1.9500, last reward: -0.0075, gradient norm: 0.5664: 49%|####8 | 305/625 [00:42<00:45, 7.05it/s]
reward: -2.5697, last reward: -0.3024, gradient norm: 22.61: 49%|####8 | 305/625 [00:42<00:45, 7.05it/s]
reward: -2.5697, last reward: -0.3024, gradient norm: 22.61: 49%|####8 | 306/625 [00:42<00:45, 7.06it/s]
reward: -2.3117, last reward: -0.0052, gradient norm: 1.006: 49%|####8 | 306/625 [00:42<00:45, 7.06it/s]
reward: -2.3117, last reward: -0.0052, gradient norm: 1.006: 49%|####9 | 307/625 [00:42<00:44, 7.09it/s]
reward: -2.0981, last reward: -0.0018, gradient norm: 0.9312: 49%|####9 | 307/625 [00:43<00:44, 7.09it/s]
reward: -2.0981, last reward: -0.0018, gradient norm: 0.9312: 49%|####9 | 308/625 [00:43<00:44, 7.05it/s]
reward: -2.5140, last reward: -0.3873, gradient norm: 3.93: 49%|####9 | 308/625 [00:43<00:44, 7.05it/s]
reward: -2.5140, last reward: -0.3873, gradient norm: 3.93: 49%|####9 | 309/625 [00:43<00:44, 7.05it/s]
reward: -2.0411, last reward: -0.2650, gradient norm: 3.183: 49%|####9 | 309/625 [00:43<00:44, 7.05it/s]
reward: -2.0411, last reward: -0.2650, gradient norm: 3.183: 50%|####9 | 310/625 [00:43<00:44, 7.04it/s]
reward: -2.1656, last reward: -0.0228, gradient norm: 2.004: 50%|####9 | 310/625 [00:43<00:44, 7.04it/s]
reward: -2.1656, last reward: -0.0228, gradient norm: 2.004: 50%|####9 | 311/625 [00:43<00:44, 7.04it/s]
reward: -2.1196, last reward: -0.2478, gradient norm: 11.78: 50%|####9 | 311/625 [00:43<00:44, 7.04it/s]
reward: -2.1196, last reward: -0.2478, gradient norm: 11.78: 50%|####9 | 312/625 [00:43<00:44, 7.04it/s]
reward: -2.7353, last reward: -3.0812, gradient norm: 82.91: 50%|####9 | 312/625 [00:43<00:44, 7.04it/s]
reward: -2.7353, last reward: -3.0812, gradient norm: 82.91: 50%|##### | 313/625 [00:43<00:44, 7.05it/s]
reward: -3.0995, last reward: -2.3022, gradient norm: 8.758: 50%|##### | 313/625 [00:43<00:44, 7.05it/s]
reward: -3.0995, last reward: -2.3022, gradient norm: 8.758: 50%|##### | 314/625 [00:43<00:44, 7.07it/s]
reward: -3.1406, last reward: -2.4626, gradient norm: 15.99: 50%|##### | 314/625 [00:44<00:44, 7.07it/s]
reward: -3.1406, last reward: -2.4626, gradient norm: 15.99: 50%|##### | 315/625 [00:44<00:43, 7.09it/s]
reward: -3.2156, last reward: -1.9055, gradient norm: 7.851: 50%|##### | 315/625 [00:44<00:43, 7.09it/s]
reward: -3.2156, last reward: -1.9055, gradient norm: 7.851: 51%|##### | 316/625 [00:44<00:43, 7.11it/s]
reward: -3.1953, last reward: -2.3774, gradient norm: 19.78: 51%|##### | 316/625 [00:44<00:43, 7.11it/s]
reward: -3.1953, last reward: -2.3774, gradient norm: 19.78: 51%|##### | 317/625 [00:44<00:43, 7.08it/s]
reward: -2.6385, last reward: -0.9917, gradient norm: 16.15: 51%|##### | 317/625 [00:44<00:43, 7.08it/s]
reward: -2.6385, last reward: -0.9917, gradient norm: 16.15: 51%|##### | 318/625 [00:44<00:43, 7.06it/s]
reward: -2.2764, last reward: -0.0536, gradient norm: 2.905: 51%|##### | 318/625 [00:44<00:43, 7.06it/s]
reward: -2.2764, last reward: -0.0536, gradient norm: 2.905: 51%|#####1 | 319/625 [00:44<00:43, 7.05it/s]
reward: -2.6391, last reward: -1.9317, gradient norm: 23.78: 51%|#####1 | 319/625 [00:44<00:43, 7.05it/s]
reward: -2.6391, last reward: -1.9317, gradient norm: 23.78: 51%|#####1 | 320/625 [00:44<00:43, 7.04it/s]
reward: -2.9748, last reward: -4.2679, gradient norm: 59.43: 51%|#####1 | 320/625 [00:44<00:43, 7.04it/s]
reward: -2.9748, last reward: -4.2679, gradient norm: 59.43: 51%|#####1 | 321/625 [00:44<00:43, 7.05it/s]
reward: -2.8495, last reward: -4.5125, gradient norm: 52.19: 51%|#####1 | 321/625 [00:45<00:43, 7.05it/s]
reward: -2.8495, last reward: -4.5125, gradient norm: 52.19: 52%|#####1 | 322/625 [00:45<00:42, 7.07it/s]
reward: -2.8177, last reward: -2.6602, gradient norm: 52.75: 52%|#####1 | 322/625 [00:45<00:42, 7.07it/s]
reward: -2.8177, last reward: -2.6602, gradient norm: 52.75: 52%|#####1 | 323/625 [00:45<00:42, 7.08it/s]
reward: -2.0704, last reward: -0.5776, gradient norm: 59.07: 52%|#####1 | 323/625 [00:45<00:42, 7.08it/s]
reward: -2.0704, last reward: -0.5776, gradient norm: 59.07: 52%|#####1 | 324/625 [00:45<00:42, 7.10it/s]
reward: -1.9833, last reward: -0.1339, gradient norm: 4.402: 52%|#####1 | 324/625 [00:45<00:42, 7.10it/s]
reward: -1.9833, last reward: -0.1339, gradient norm: 4.402: 52%|#####2 | 325/625 [00:45<00:42, 7.12it/s]
reward: -2.2760, last reward: -2.1238, gradient norm: 30.36: 52%|#####2 | 325/625 [00:45<00:42, 7.12it/s]
reward: -2.2760, last reward: -2.1238, gradient norm: 30.36: 52%|#####2 | 326/625 [00:45<00:41, 7.13it/s]
reward: -2.9299, last reward: -5.0227, gradient norm: 100.5: 52%|#####2 | 326/625 [00:45<00:41, 7.13it/s]
reward: -2.9299, last reward: -5.0227, gradient norm: 100.5: 52%|#####2 | 327/625 [00:45<00:41, 7.14it/s]
reward: -2.7727, last reward: -2.1607, gradient norm: 336.7: 52%|#####2 | 327/625 [00:45<00:41, 7.14it/s]
reward: -2.7727, last reward: -2.1607, gradient norm: 336.7: 52%|#####2 | 328/625 [00:45<00:41, 7.13it/s]
reward: -2.3958, last reward: -0.3223, gradient norm: 2.763: 52%|#####2 | 328/625 [00:46<00:41, 7.13it/s]
reward: -2.3958, last reward: -0.3223, gradient norm: 2.763: 53%|#####2 | 329/625 [00:46<00:41, 7.12it/s]
reward: -2.4742, last reward: -0.1797, gradient norm: 47.32: 53%|#####2 | 329/625 [00:46<00:41, 7.12it/s]
reward: -2.4742, last reward: -0.1797, gradient norm: 47.32: 53%|#####2 | 330/625 [00:46<00:41, 7.14it/s]
reward: -2.0144, last reward: -0.0085, gradient norm: 4.791: 53%|#####2 | 330/625 [00:46<00:41, 7.14it/s]
reward: -2.0144, last reward: -0.0085, gradient norm: 4.791: 53%|#####2 | 331/625 [00:46<00:41, 7.13it/s]
reward: -1.8284, last reward: -0.0428, gradient norm: 12.29: 53%|#####2 | 331/625 [00:46<00:41, 7.13it/s]
reward: -1.8284, last reward: -0.0428, gradient norm: 12.29: 53%|#####3 | 332/625 [00:46<00:41, 7.14it/s]
reward: -2.5229, last reward: -0.0098, gradient norm: 0.7365: 53%|#####3 | 332/625 [00:46<00:41, 7.14it/s]
reward: -2.5229, last reward: -0.0098, gradient norm: 0.7365: 53%|#####3 | 333/625 [00:46<00:40, 7.14it/s]
reward: -2.4566, last reward: -0.0781, gradient norm: 2.086: 53%|#####3 | 333/625 [00:46<00:40, 7.14it/s]
reward: -2.4566, last reward: -0.0781, gradient norm: 2.086: 53%|#####3 | 334/625 [00:46<00:40, 7.13it/s]
reward: -2.3355, last reward: -0.0230, gradient norm: 1.311: 53%|#####3 | 334/625 [00:46<00:40, 7.13it/s]
reward: -2.3355, last reward: -0.0230, gradient norm: 1.311: 54%|#####3 | 335/625 [00:46<00:40, 7.12it/s]
reward: -1.9346, last reward: -0.0423, gradient norm: 1.076: 54%|#####3 | 335/625 [00:46<00:40, 7.12it/s]
reward: -1.9346, last reward: -0.0423, gradient norm: 1.076: 54%|#####3 | 336/625 [00:46<00:40, 7.09it/s]
reward: -2.3711, last reward: -0.1335, gradient norm: 0.6855: 54%|#####3 | 336/625 [00:47<00:40, 7.09it/s]
reward: -2.3711, last reward: -0.1335, gradient norm: 0.6855: 54%|#####3 | 337/625 [00:47<00:40, 7.12it/s]
reward: -2.0304, last reward: -0.0023, gradient norm: 0.8459: 54%|#####3 | 337/625 [00:47<00:40, 7.12it/s]
reward: -2.0304, last reward: -0.0023, gradient norm: 0.8459: 54%|#####4 | 338/625 [00:47<00:40, 7.13it/s]
reward: -1.9998, last reward: -0.4399, gradient norm: 13.1: 54%|#####4 | 338/625 [00:47<00:40, 7.13it/s]
reward: -1.9998, last reward: -0.4399, gradient norm: 13.1: 54%|#####4 | 339/625 [00:47<00:40, 7.13it/s]
reward: -2.2303, last reward: -2.1346, gradient norm: 45.99: 54%|#####4 | 339/625 [00:47<00:40, 7.13it/s]
reward: -2.2303, last reward: -2.1346, gradient norm: 45.99: 54%|#####4 | 340/625 [00:47<00:40, 7.10it/s]
reward: -2.2915, last reward: -1.7116, gradient norm: 40.34: 54%|#####4 | 340/625 [00:47<00:40, 7.10it/s]
reward: -2.2915, last reward: -1.7116, gradient norm: 40.34: 55%|#####4 | 341/625 [00:47<00:40, 7.08it/s]
reward: -2.5560, last reward: -0.0487, gradient norm: 1.195: 55%|#####4 | 341/625 [00:47<00:40, 7.08it/s]
reward: -2.5560, last reward: -0.0487, gradient norm: 1.195: 55%|#####4 | 342/625 [00:47<00:39, 7.10it/s]
reward: -2.5119, last reward: -0.0358, gradient norm: 1.061: 55%|#####4 | 342/625 [00:47<00:39, 7.10it/s]
reward: -2.5119, last reward: -0.0358, gradient norm: 1.061: 55%|#####4 | 343/625 [00:47<00:39, 7.10it/s]
reward: -2.3305, last reward: -0.3705, gradient norm: 1.957: 55%|#####4 | 343/625 [00:48<00:39, 7.10it/s]
reward: -2.3305, last reward: -0.3705, gradient norm: 1.957: 55%|#####5 | 344/625 [00:48<00:39, 7.09it/s]
reward: -2.6068, last reward: -0.2112, gradient norm: 13.83: 55%|#####5 | 344/625 [00:48<00:39, 7.09it/s]
reward: -2.6068, last reward: -0.2112, gradient norm: 13.83: 55%|#####5 | 345/625 [00:48<00:39, 7.08it/s]
reward: -2.5731, last reward: -1.8455, gradient norm: 66.75: 55%|#####5 | 345/625 [00:48<00:39, 7.08it/s]
reward: -2.5731, last reward: -1.8455, gradient norm: 66.75: 55%|#####5 | 346/625 [00:48<00:39, 7.10it/s]
reward: -2.3897, last reward: -0.0376, gradient norm: 1.608: 55%|#####5 | 346/625 [00:48<00:39, 7.10it/s]
reward: -2.3897, last reward: -0.0376, gradient norm: 1.608: 56%|#####5 | 347/625 [00:48<00:39, 7.08it/s]
reward: -2.2264, last reward: -0.0434, gradient norm: 2.012: 56%|#####5 | 347/625 [00:48<00:39, 7.08it/s]
reward: -2.2264, last reward: -0.0434, gradient norm: 2.012: 56%|#####5 | 348/625 [00:48<00:39, 7.07it/s]
reward: -2.1300, last reward: -0.1215, gradient norm: 2.557: 56%|#####5 | 348/625 [00:48<00:39, 7.07it/s]
reward: -2.1300, last reward: -0.1215, gradient norm: 2.557: 56%|#####5 | 349/625 [00:48<00:39, 7.07it/s]
reward: -2.0968, last reward: -0.0885, gradient norm: 3.389: 56%|#####5 | 349/625 [00:48<00:39, 7.07it/s]
reward: -2.0968, last reward: -0.0885, gradient norm: 3.389: 56%|#####6 | 350/625 [00:48<00:38, 7.05it/s]
reward: -2.1348, last reward: -0.0073, gradient norm: 0.5052: 56%|#####6 | 350/625 [00:49<00:38, 7.05it/s]
reward: -2.1348, last reward: -0.0073, gradient norm: 0.5052: 56%|#####6 | 351/625 [00:49<00:38, 7.06it/s]
reward: -2.4184, last reward: -3.2817, gradient norm: 108.6: 56%|#####6 | 351/625 [00:49<00:38, 7.06it/s]
reward: -2.4184, last reward: -3.2817, gradient norm: 108.6: 56%|#####6 | 352/625 [00:49<00:38, 7.05it/s]
reward: -2.3774, last reward: -1.8887, gradient norm: 54.07: 56%|#####6 | 352/625 [00:49<00:38, 7.05it/s]
reward: -2.3774, last reward: -1.8887, gradient norm: 54.07: 56%|#####6 | 353/625 [00:49<00:38, 7.09it/s]
reward: -2.4779, last reward: -0.1009, gradient norm: 10.91: 56%|#####6 | 353/625 [00:49<00:38, 7.09it/s]
reward: -2.4779, last reward: -0.1009, gradient norm: 10.91: 57%|#####6 | 354/625 [00:49<00:38, 7.11it/s]
reward: -2.2588, last reward: -0.0604, gradient norm: 2.599: 57%|#####6 | 354/625 [00:49<00:38, 7.11it/s]
reward: -2.2588, last reward: -0.0604, gradient norm: 2.599: 57%|#####6 | 355/625 [00:49<00:37, 7.12it/s]
reward: -2.4486, last reward: -0.1176, gradient norm: 3.656: 57%|#####6 | 355/625 [00:49<00:37, 7.12it/s]
reward: -2.4486, last reward: -0.1176, gradient norm: 3.656: 57%|#####6 | 356/625 [00:49<00:37, 7.14it/s]
reward: -2.2436, last reward: -0.0668, gradient norm: 2.724: 57%|#####6 | 356/625 [00:49<00:37, 7.14it/s]
reward: -2.2436, last reward: -0.0668, gradient norm: 2.724: 57%|#####7 | 357/625 [00:49<00:37, 7.15it/s]
reward: -1.8849, last reward: -0.0012, gradient norm: 5.326: 57%|#####7 | 357/625 [00:50<00:37, 7.15it/s]
reward: -1.8849, last reward: -0.0012, gradient norm: 5.326: 57%|#####7 | 358/625 [00:50<00:37, 7.15it/s]
reward: -2.7511, last reward: -0.8804, gradient norm: 13.6: 57%|#####7 | 358/625 [00:50<00:37, 7.15it/s]
reward: -2.7511, last reward: -0.8804, gradient norm: 13.6: 57%|#####7 | 359/625 [00:50<00:37, 7.14it/s]
reward: -2.8870, last reward: -3.6728, gradient norm: 33.56: 57%|#####7 | 359/625 [00:50<00:37, 7.14it/s]
reward: -2.8870, last reward: -3.6728, gradient norm: 33.56: 58%|#####7 | 360/625 [00:50<00:37, 7.10it/s]
reward: -2.8841, last reward: -2.5508, gradient norm: 30.93: 58%|#####7 | 360/625 [00:50<00:37, 7.10it/s]
reward: -2.8841, last reward: -2.5508, gradient norm: 30.93: 58%|#####7 | 361/625 [00:50<00:37, 7.07it/s]
reward: -2.5242, last reward: -1.0268, gradient norm: 33.15: 58%|#####7 | 361/625 [00:50<00:37, 7.07it/s]
reward: -2.5242, last reward: -1.0268, gradient norm: 33.15: 58%|#####7 | 362/625 [00:50<00:37, 7.07it/s]
reward: -2.3232, last reward: -0.0013, gradient norm: 0.6185: 58%|#####7 | 362/625 [00:50<00:37, 7.07it/s]
reward: -2.3232, last reward: -0.0013, gradient norm: 0.6185: 58%|#####8 | 363/625 [00:50<00:37, 7.06it/s]
reward: -2.1378, last reward: -0.0204, gradient norm: 1.337: 58%|#####8 | 363/625 [00:50<00:37, 7.06it/s]
reward: -2.1378, last reward: -0.0204, gradient norm: 1.337: 58%|#####8 | 364/625 [00:50<00:36, 7.07it/s]
reward: -2.2677, last reward: -0.0355, gradient norm: 1.685: 58%|#####8 | 364/625 [00:51<00:36, 7.07it/s]
reward: -2.2677, last reward: -0.0355, gradient norm: 1.685: 58%|#####8 | 365/625 [00:51<00:36, 7.08it/s]
reward: -2.4884, last reward: -0.0231, gradient norm: 1.213: 58%|#####8 | 365/625 [00:51<00:36, 7.08it/s]
reward: -2.4884, last reward: -0.0231, gradient norm: 1.213: 59%|#####8 | 366/625 [00:51<00:36, 7.06it/s]
reward: -2.0770, last reward: -0.0014, gradient norm: 0.6793: 59%|#####8 | 366/625 [00:51<00:36, 7.06it/s]
reward: -2.0770, last reward: -0.0014, gradient norm: 0.6793: 59%|#####8 | 367/625 [00:51<00:36, 7.07it/s]
reward: -1.9834, last reward: -0.0349, gradient norm: 1.863: 59%|#####8 | 367/625 [00:51<00:36, 7.07it/s]
reward: -1.9834, last reward: -0.0349, gradient norm: 1.863: 59%|#####8 | 368/625 [00:51<00:36, 7.06it/s]
reward: -2.6709, last reward: -0.1416, gradient norm: 5.462: 59%|#####8 | 368/625 [00:51<00:36, 7.06it/s]
reward: -2.6709, last reward: -0.1416, gradient norm: 5.462: 59%|#####9 | 369/625 [00:51<00:36, 7.05it/s]
reward: -2.5199, last reward: -3.9790, gradient norm: 47.67: 59%|#####9 | 369/625 [00:51<00:36, 7.05it/s]
reward: -2.5199, last reward: -3.9790, gradient norm: 47.67: 59%|#####9 | 370/625 [00:51<00:36, 7.04it/s]
reward: -2.9401, last reward: -3.7802, gradient norm: 32.47: 59%|#####9 | 370/625 [00:51<00:36, 7.04it/s]
reward: -2.9401, last reward: -3.7802, gradient norm: 32.47: 59%|#####9 | 371/625 [00:51<00:36, 7.04it/s]
reward: -2.6723, last reward: -3.6507, gradient norm: 45.1: 59%|#####9 | 371/625 [00:52<00:36, 7.04it/s]
reward: -2.6723, last reward: -3.6507, gradient norm: 45.1: 60%|#####9 | 372/625 [00:52<00:35, 7.05it/s]
reward: -2.2678, last reward: -0.6201, gradient norm: 32.94: 60%|#####9 | 372/625 [00:52<00:35, 7.05it/s]
reward: -2.2678, last reward: -0.6201, gradient norm: 32.94: 60%|#####9 | 373/625 [00:52<00:35, 7.04it/s]
reward: -2.2184, last reward: -0.0075, gradient norm: 0.7385: 60%|#####9 | 373/625 [00:52<00:35, 7.04it/s]
reward: -2.2184, last reward: -0.0075, gradient norm: 0.7385: 60%|#####9 | 374/625 [00:52<00:35, 7.05it/s]
reward: -2.6344, last reward: -0.0576, gradient norm: 1.617: 60%|#####9 | 374/625 [00:52<00:35, 7.05it/s]
reward: -2.6344, last reward: -0.0576, gradient norm: 1.617: 60%|###### | 375/625 [00:52<00:35, 7.06it/s]
reward: -1.9945, last reward: -0.0772, gradient norm: 2.567: 60%|###### | 375/625 [00:52<00:35, 7.06it/s]
reward: -1.9945, last reward: -0.0772, gradient norm: 2.567: 60%|###### | 376/625 [00:52<00:35, 7.07it/s]
reward: -1.7576, last reward: -0.0398, gradient norm: 1.961: 60%|###### | 376/625 [00:52<00:35, 7.07it/s]
reward: -1.7576, last reward: -0.0398, gradient norm: 1.961: 60%|###### | 377/625 [00:52<00:35, 7.07it/s]
reward: -2.3396, last reward: -0.0022, gradient norm: 1.094: 60%|###### | 377/625 [00:52<00:35, 7.07it/s]
reward: -2.3396, last reward: -0.0022, gradient norm: 1.094: 60%|###### | 378/625 [00:52<00:34, 7.06it/s]
reward: -2.3073, last reward: -0.4018, gradient norm: 29.23: 60%|###### | 378/625 [00:53<00:34, 7.06it/s]
reward: -2.3073, last reward: -0.4018, gradient norm: 29.23: 61%|###### | 379/625 [00:53<00:34, 7.08it/s]
reward: -2.3313, last reward: -1.1869, gradient norm: 38.62: 61%|###### | 379/625 [00:53<00:34, 7.08it/s]
reward: -2.3313, last reward: -1.1869, gradient norm: 38.62: 61%|###### | 380/625 [00:53<00:34, 7.07it/s]
reward: -2.0481, last reward: -0.1117, gradient norm: 5.321: 61%|###### | 380/625 [00:53<00:34, 7.07it/s]
reward: -2.0481, last reward: -0.1117, gradient norm: 5.321: 61%|###### | 381/625 [00:53<00:34, 7.07it/s]
reward: -1.6823, last reward: -0.0001, gradient norm: 1.981: 61%|###### | 381/625 [00:53<00:34, 7.07it/s]
reward: -1.6823, last reward: -0.0001, gradient norm: 1.981: 61%|######1 | 382/625 [00:53<00:34, 7.10it/s]
reward: -1.8305, last reward: -0.0210, gradient norm: 1.228: 61%|######1 | 382/625 [00:53<00:34, 7.10it/s]
reward: -1.8305, last reward: -0.0210, gradient norm: 1.228: 61%|######1 | 383/625 [00:53<00:34, 7.08it/s]
reward: -1.4908, last reward: -0.0272, gradient norm: 1.538: 61%|######1 | 383/625 [00:53<00:34, 7.08it/s]
reward: -1.4908, last reward: -0.0272, gradient norm: 1.538: 61%|######1 | 384/625 [00:53<00:34, 7.06it/s]
reward: -2.3267, last reward: -0.0111, gradient norm: 0.7965: 61%|######1 | 384/625 [00:53<00:34, 7.06it/s]
reward: -2.3267, last reward: -0.0111, gradient norm: 0.7965: 62%|######1 | 385/625 [00:53<00:34, 7.04it/s]
reward: -2.1796, last reward: -0.0039, gradient norm: 0.5396: 62%|######1 | 385/625 [00:54<00:34, 7.04it/s]
reward: -2.1796, last reward: -0.0039, gradient norm: 0.5396: 62%|######1 | 386/625 [00:54<00:33, 7.04it/s]
reward: -2.3757, last reward: -0.0490, gradient norm: 2.237: 62%|######1 | 386/625 [00:54<00:33, 7.04it/s]
reward: -2.3757, last reward: -0.0490, gradient norm: 2.237: 62%|######1 | 387/625 [00:54<00:33, 7.04it/s]
reward: -2.1394, last reward: -0.4187, gradient norm: 52.11: 62%|######1 | 387/625 [00:54<00:33, 7.04it/s]
reward: -2.1394, last reward: -0.4187, gradient norm: 52.11: 62%|######2 | 388/625 [00:54<00:33, 7.07it/s]
reward: -2.2986, last reward: -0.0038, gradient norm: 0.7954: 62%|######2 | 388/625 [00:54<00:33, 7.07it/s]
reward: -2.2986, last reward: -0.0038, gradient norm: 0.7954: 62%|######2 | 389/625 [00:54<00:33, 7.11it/s]
reward: -2.1274, last reward: -0.0063, gradient norm: 0.813: 62%|######2 | 389/625 [00:54<00:33, 7.11it/s]
reward: -2.1274, last reward: -0.0063, gradient norm: 0.813: 62%|######2 | 390/625 [00:54<00:33, 7.11it/s]
reward: -1.8706, last reward: -0.0114, gradient norm: 3.325: 62%|######2 | 390/625 [00:54<00:33, 7.11it/s]
reward: -1.8706, last reward: -0.0114, gradient norm: 3.325: 63%|######2 | 391/625 [00:54<00:32, 7.11it/s]
reward: -1.6922, last reward: -0.0004, gradient norm: 0.2423: 63%|######2 | 391/625 [00:54<00:32, 7.11it/s]
reward: -1.6922, last reward: -0.0004, gradient norm: 0.2423: 63%|######2 | 392/625 [00:54<00:32, 7.10it/s]
reward: -1.9115, last reward: -0.2602, gradient norm: 2.599: 63%|######2 | 392/625 [00:55<00:32, 7.10it/s]
reward: -1.9115, last reward: -0.2602, gradient norm: 2.599: 63%|######2 | 393/625 [00:55<00:32, 7.09it/s]
reward: -2.2449, last reward: -0.0783, gradient norm: 5.199: 63%|######2 | 393/625 [00:55<00:32, 7.09it/s]
reward: -2.2449, last reward: -0.0783, gradient norm: 5.199: 63%|######3 | 394/625 [00:55<00:32, 7.07it/s]
reward: -2.0631, last reward: -0.0057, gradient norm: 0.7444: 63%|######3 | 394/625 [00:55<00:32, 7.07it/s]
reward: -2.0631, last reward: -0.0057, gradient norm: 0.7444: 63%|######3 | 395/625 [00:55<00:32, 7.09it/s]
reward: -2.3339, last reward: -0.0167, gradient norm: 1.39: 63%|######3 | 395/625 [00:55<00:32, 7.09it/s]
reward: -2.3339, last reward: -0.0167, gradient norm: 1.39: 63%|######3 | 396/625 [00:55<00:32, 7.12it/s]
reward: -2.4806, last reward: -0.0023, gradient norm: 2.317: 63%|######3 | 396/625 [00:55<00:32, 7.12it/s]
reward: -2.4806, last reward: -0.0023, gradient norm: 2.317: 64%|######3 | 397/625 [00:55<00:31, 7.14it/s]
reward: -2.4171, last reward: -0.1438, gradient norm: 5.067: 64%|######3 | 397/625 [00:55<00:31, 7.14it/s]
reward: -2.4171, last reward: -0.1438, gradient norm: 5.067: 64%|######3 | 398/625 [00:55<00:31, 7.12it/s]
reward: -2.2618, last reward: -0.5809, gradient norm: 20.39: 64%|######3 | 398/625 [00:55<00:31, 7.12it/s]
reward: -2.2618, last reward: -0.5809, gradient norm: 20.39: 64%|######3 | 399/625 [00:55<00:31, 7.13it/s]
reward: -2.0115, last reward: -0.0054, gradient norm: 0.3364: 64%|######3 | 399/625 [00:56<00:31, 7.13it/s]
reward: -2.0115, last reward: -0.0054, gradient norm: 0.3364: 64%|######4 | 400/625 [00:56<00:31, 7.12it/s]
reward: -1.8733, last reward: -0.0184, gradient norm: 2.275: 64%|######4 | 400/625 [00:56<00:31, 7.12it/s]
reward: -1.8733, last reward: -0.0184, gradient norm: 2.275: 64%|######4 | 401/625 [00:56<00:31, 7.09it/s]
reward: -1.9137, last reward: -0.0113, gradient norm: 1.025: 64%|######4 | 401/625 [00:56<00:31, 7.09it/s]
reward: -1.9137, last reward: -0.0113, gradient norm: 1.025: 64%|######4 | 402/625 [00:56<00:31, 7.08it/s]
reward: -2.0386, last reward: -0.0625, gradient norm: 2.763: 64%|######4 | 402/625 [00:56<00:31, 7.08it/s]
reward: -2.0386, last reward: -0.0625, gradient norm: 2.763: 64%|######4 | 403/625 [00:56<00:31, 7.06it/s]
reward: -2.1332, last reward: -0.0582, gradient norm: 0.7816: 64%|######4 | 403/625 [00:56<00:31, 7.06it/s]
reward: -2.1332, last reward: -0.0582, gradient norm: 0.7816: 65%|######4 | 404/625 [00:56<00:31, 7.06it/s]
reward: -1.8341, last reward: -0.0941, gradient norm: 5.854: 65%|######4 | 404/625 [00:56<00:31, 7.06it/s]
reward: -1.8341, last reward: -0.0941, gradient norm: 5.854: 65%|######4 | 405/625 [00:56<00:31, 7.08it/s]
reward: -1.8615, last reward: -0.0968, gradient norm: 4.588: 65%|######4 | 405/625 [00:56<00:31, 7.08it/s]
reward: -1.8615, last reward: -0.0968, gradient norm: 4.588: 65%|######4 | 406/625 [00:56<00:30, 7.08it/s]
reward: -2.0981, last reward: -0.3849, gradient norm: 6.008: 65%|######4 | 406/625 [00:57<00:30, 7.08it/s]
reward: -2.0981, last reward: -0.3849, gradient norm: 6.008: 65%|######5 | 407/625 [00:57<00:30, 7.07it/s]
reward: -1.9395, last reward: -0.0765, gradient norm: 4.055: 65%|######5 | 407/625 [00:57<00:30, 7.07it/s]
reward: -1.9395, last reward: -0.0765, gradient norm: 4.055: 65%|######5 | 408/625 [00:57<00:30, 7.09it/s]
reward: -2.2685, last reward: -0.2235, gradient norm: 1.688: 65%|######5 | 408/625 [00:57<00:30, 7.09it/s]
reward: -2.2685, last reward: -0.2235, gradient norm: 1.688: 65%|######5 | 409/625 [00:57<00:30, 7.08it/s]
reward: -2.3052, last reward: -1.4249, gradient norm: 25.99: 65%|######5 | 409/625 [00:57<00:30, 7.08it/s]
reward: -2.3052, last reward: -1.4249, gradient norm: 25.99: 66%|######5 | 410/625 [00:57<00:30, 7.08it/s]
reward: -2.6806, last reward: -1.6383, gradient norm: 30.59: 66%|######5 | 410/625 [00:57<00:30, 7.08it/s]
reward: -2.6806, last reward: -1.6383, gradient norm: 30.59: 66%|######5 | 411/625 [00:57<00:30, 7.06it/s]
reward: -2.3721, last reward: -2.9981, gradient norm: 74.37: 66%|######5 | 411/625 [00:57<00:30, 7.06it/s]
reward: -2.3721, last reward: -2.9981, gradient norm: 74.37: 66%|######5 | 412/625 [00:57<00:30, 7.05it/s]
reward: -2.1862, last reward: -0.0063, gradient norm: 1.822: 66%|######5 | 412/625 [00:57<00:30, 7.05it/s]
reward: -2.1862, last reward: -0.0063, gradient norm: 1.822: 66%|######6 | 413/625 [00:57<00:30, 7.05it/s]
reward: -1.9811, last reward: -0.0171, gradient norm: 1.013: 66%|######6 | 413/625 [00:58<00:30, 7.05it/s]
reward: -1.9811, last reward: -0.0171, gradient norm: 1.013: 66%|######6 | 414/625 [00:58<00:29, 7.05it/s]
reward: -2.0252, last reward: -0.0049, gradient norm: 0.6205: 66%|######6 | 414/625 [00:58<00:29, 7.05it/s]
reward: -2.0252, last reward: -0.0049, gradient norm: 0.6205: 66%|######6 | 415/625 [00:58<00:29, 7.07it/s]
reward: -2.1108, last reward: -0.4921, gradient norm: 23.74: 66%|######6 | 415/625 [00:58<00:29, 7.07it/s]
reward: -2.1108, last reward: -0.4921, gradient norm: 23.74: 67%|######6 | 416/625 [00:58<00:29, 7.05it/s]
reward: -1.9142, last reward: -0.8130, gradient norm: 52.65: 67%|######6 | 416/625 [00:58<00:29, 7.05it/s]
reward: -1.9142, last reward: -0.8130, gradient norm: 52.65: 67%|######6 | 417/625 [00:58<00:29, 7.04it/s]
reward: -2.1725, last reward: -0.0036, gradient norm: 0.3196: 67%|######6 | 417/625 [00:58<00:29, 7.04it/s]
reward: -2.1725, last reward: -0.0036, gradient norm: 0.3196: 67%|######6 | 418/625 [00:58<00:29, 7.04it/s]
reward: -1.7795, last reward: -0.0242, gradient norm: 1.799: 67%|######6 | 418/625 [00:58<00:29, 7.04it/s]
reward: -1.7795, last reward: -0.0242, gradient norm: 1.799: 67%|######7 | 419/625 [00:58<00:29, 7.07it/s]
reward: -1.7737, last reward: -0.0138, gradient norm: 1.39: 67%|######7 | 419/625 [00:58<00:29, 7.07it/s]
reward: -1.7737, last reward: -0.0138, gradient norm: 1.39: 67%|######7 | 420/625 [00:58<00:28, 7.10it/s]
reward: -2.1462, last reward: -0.0053, gradient norm: 0.47: 67%|######7 | 420/625 [00:58<00:28, 7.10it/s]
reward: -2.1462, last reward: -0.0053, gradient norm: 0.47: 67%|######7 | 421/625 [00:58<00:28, 7.11it/s]
reward: -1.9226, last reward: -0.6139, gradient norm: 40.3: 67%|######7 | 421/625 [00:59<00:28, 7.11it/s]
reward: -1.9226, last reward: -0.6139, gradient norm: 40.3: 68%|######7 | 422/625 [00:59<00:28, 7.13it/s]
reward: -1.9889, last reward: -0.0403, gradient norm: 1.112: 68%|######7 | 422/625 [00:59<00:28, 7.13it/s]
reward: -1.9889, last reward: -0.0403, gradient norm: 1.112: 68%|######7 | 423/625 [00:59<00:28, 7.13it/s]
reward: -1.6194, last reward: -0.0032, gradient norm: 0.79: 68%|######7 | 423/625 [00:59<00:28, 7.13it/s]
reward: -1.6194, last reward: -0.0032, gradient norm: 0.79: 68%|######7 | 424/625 [00:59<00:28, 7.14it/s]
reward: -2.3989, last reward: -0.0104, gradient norm: 1.134: 68%|######7 | 424/625 [00:59<00:28, 7.14it/s]
reward: -2.3989, last reward: -0.0104, gradient norm: 1.134: 68%|######8 | 425/625 [00:59<00:28, 7.14it/s]
reward: -1.9960, last reward: -0.0009, gradient norm: 0.6009: 68%|######8 | 425/625 [00:59<00:28, 7.14it/s]
reward: -1.9960, last reward: -0.0009, gradient norm: 0.6009: 68%|######8 | 426/625 [00:59<00:27, 7.14it/s]
reward: -2.2697, last reward: -0.0914, gradient norm: 2.905: 68%|######8 | 426/625 [00:59<00:27, 7.14it/s]
reward: -2.2697, last reward: -0.0914, gradient norm: 2.905: 68%|######8 | 427/625 [00:59<00:27, 7.11it/s]
reward: -2.4256, last reward: -0.1114, gradient norm: 2.102: 68%|######8 | 427/625 [00:59<00:27, 7.11it/s]
reward: -2.4256, last reward: -0.1114, gradient norm: 2.102: 68%|######8 | 428/625 [00:59<00:27, 7.09it/s]
reward: -1.9862, last reward: -0.1932, gradient norm: 22.44: 68%|######8 | 428/625 [01:00<00:27, 7.09it/s]
reward: -1.9862, last reward: -0.1932, gradient norm: 22.44: 69%|######8 | 429/625 [01:00<00:27, 7.08it/s]
reward: -2.0637, last reward: -0.0623, gradient norm: 3.082: 69%|######8 | 429/625 [01:00<00:27, 7.08it/s]
reward: -2.0637, last reward: -0.0623, gradient norm: 3.082: 69%|######8 | 430/625 [01:00<00:27, 7.06it/s]
reward: -1.9906, last reward: -0.2031, gradient norm: 5.5: 69%|######8 | 430/625 [01:00<00:27, 7.06it/s]
reward: -1.9906, last reward: -0.2031, gradient norm: 5.5: 69%|######8 | 431/625 [01:00<00:27, 7.06it/s]
reward: -1.9948, last reward: -0.0895, gradient norm: 3.456: 69%|######8 | 431/625 [01:00<00:27, 7.06it/s]
reward: -1.9948, last reward: -0.0895, gradient norm: 3.456: 69%|######9 | 432/625 [01:00<00:27, 7.06it/s]
reward: -2.1970, last reward: -0.0256, gradient norm: 1.593: 69%|######9 | 432/625 [01:00<00:27, 7.06it/s]
reward: -2.1970, last reward: -0.0256, gradient norm: 1.593: 69%|######9 | 433/625 [01:00<00:27, 7.05it/s]
reward: -2.4231, last reward: -0.0449, gradient norm: 3.644: 69%|######9 | 433/625 [01:00<00:27, 7.05it/s]
reward: -2.4231, last reward: -0.0449, gradient norm: 3.644: 69%|######9 | 434/625 [01:00<00:27, 7.04it/s]
reward: -2.1039, last reward: -3.1973, gradient norm: 87.37: 69%|######9 | 434/625 [01:00<00:27, 7.04it/s]
reward: -2.1039, last reward: -3.1973, gradient norm: 87.37: 70%|######9 | 435/625 [01:00<00:26, 7.04it/s]
reward: -2.4561, last reward: -0.1225, gradient norm: 6.119: 70%|######9 | 435/625 [01:01<00:26, 7.04it/s]
reward: -2.4561, last reward: -0.1225, gradient norm: 6.119: 70%|######9 | 436/625 [01:01<00:26, 7.05it/s]
reward: -2.0211, last reward: -0.2125, gradient norm: 2.94: 70%|######9 | 436/625 [01:01<00:26, 7.05it/s]
reward: -2.0211, last reward: -0.2125, gradient norm: 2.94: 70%|######9 | 437/625 [01:01<00:26, 7.06it/s]
reward: -2.3866, last reward: -0.0050, gradient norm: 0.7202: 70%|######9 | 437/625 [01:01<00:26, 7.06it/s]
reward: -2.3866, last reward: -0.0050, gradient norm: 0.7202: 70%|####### | 438/625 [01:01<00:26, 7.04it/s]
reward: -1.6388, last reward: -0.0072, gradient norm: 0.8657: 70%|####### | 438/625 [01:01<00:26, 7.04it/s]
reward: -1.6388, last reward: -0.0072, gradient norm: 0.8657: 70%|####### | 439/625 [01:01<00:26, 7.05it/s]
reward: -2.1187, last reward: -0.0015, gradient norm: 0.5116: 70%|####### | 439/625 [01:01<00:26, 7.05it/s]
reward: -2.1187, last reward: -0.0015, gradient norm: 0.5116: 70%|####### | 440/625 [01:01<00:26, 7.05it/s]
reward: -2.0432, last reward: -0.0025, gradient norm: 0.7809: 70%|####### | 440/625 [01:01<00:26, 7.05it/s]
reward: -2.0432, last reward: -0.0025, gradient norm: 0.7809: 71%|####### | 441/625 [01:01<00:26, 7.04it/s]
reward: -2.1925, last reward: -0.0103, gradient norm: 2.83: 71%|####### | 441/625 [01:01<00:26, 7.04it/s]
reward: -2.1925, last reward: -0.0103, gradient norm: 2.83: 71%|####### | 442/625 [01:01<00:25, 7.04it/s]
reward: -1.9570, last reward: -0.0002, gradient norm: 0.35: 71%|####### | 442/625 [01:02<00:25, 7.04it/s]
reward: -1.9570, last reward: -0.0002, gradient norm: 0.35: 71%|####### | 443/625 [01:02<00:25, 7.05it/s]
reward: -2.0871, last reward: -0.0022, gradient norm: 0.5601: 71%|####### | 443/625 [01:02<00:25, 7.05it/s]
reward: -2.0871, last reward: -0.0022, gradient norm: 0.5601: 71%|#######1 | 444/625 [01:02<00:25, 7.04it/s]
reward: -2.0165, last reward: -0.0047, gradient norm: 0.6061: 71%|#######1 | 444/625 [01:02<00:25, 7.04it/s]
reward: -2.0165, last reward: -0.0047, gradient norm: 0.6061: 71%|#######1 | 445/625 [01:02<00:25, 7.04it/s]
reward: -2.2746, last reward: -0.0027, gradient norm: 0.7887: 71%|#######1 | 445/625 [01:02<00:25, 7.04it/s]
reward: -2.2746, last reward: -0.0027, gradient norm: 0.7887: 71%|#######1 | 446/625 [01:02<00:25, 7.03it/s]
reward: -2.1835, last reward: -0.0035, gradient norm: 0.855: 71%|#######1 | 446/625 [01:02<00:25, 7.03it/s]
reward: -2.1835, last reward: -0.0035, gradient norm: 0.855: 72%|#######1 | 447/625 [01:02<00:25, 7.03it/s]
reward: -1.8420, last reward: -0.0103, gradient norm: 1.548: 72%|#######1 | 447/625 [01:02<00:25, 7.03it/s]
reward: -1.8420, last reward: -0.0103, gradient norm: 1.548: 72%|#######1 | 448/625 [01:02<00:25, 7.05it/s]
reward: -2.2653, last reward: -0.0126, gradient norm: 0.9736: 72%|#######1 | 448/625 [01:02<00:25, 7.05it/s]
reward: -2.2653, last reward: -0.0126, gradient norm: 0.9736: 72%|#######1 | 449/625 [01:02<00:24, 7.07it/s]
reward: -2.0594, last reward: -0.0119, gradient norm: 0.6196: 72%|#######1 | 449/625 [01:03<00:24, 7.07it/s]
reward: -2.0594, last reward: -0.0119, gradient norm: 0.6196: 72%|#######2 | 450/625 [01:03<00:24, 7.08it/s]
reward: -2.4509, last reward: -0.0373, gradient norm: 11.44: 72%|#######2 | 450/625 [01:03<00:24, 7.08it/s]
reward: -2.4509, last reward: -0.0373, gradient norm: 11.44: 72%|#######2 | 451/625 [01:03<00:24, 7.06it/s]
reward: -2.2528, last reward: -0.0620, gradient norm: 3.992: 72%|#######2 | 451/625 [01:03<00:24, 7.06it/s]
reward: -2.2528, last reward: -0.0620, gradient norm: 3.992: 72%|#######2 | 452/625 [01:03<00:24, 7.08it/s]
reward: -1.6898, last reward: -0.3235, gradient norm: 6.687: 72%|#######2 | 452/625 [01:03<00:24, 7.08it/s]
reward: -1.6898, last reward: -0.3235, gradient norm: 6.687: 72%|#######2 | 453/625 [01:03<00:24, 7.09it/s]
reward: -1.5879, last reward: -0.0905, gradient norm: 2.84: 72%|#######2 | 453/625 [01:03<00:24, 7.09it/s]
reward: -1.5879, last reward: -0.0905, gradient norm: 2.84: 73%|#######2 | 454/625 [01:03<00:24, 7.08it/s]
reward: -1.8406, last reward: -0.0694, gradient norm: 2.288: 73%|#######2 | 454/625 [01:03<00:24, 7.08it/s]
reward: -1.8406, last reward: -0.0694, gradient norm: 2.288: 73%|#######2 | 455/625 [01:03<00:23, 7.09it/s]
reward: -1.8259, last reward: -0.0235, gradient norm: 1.304: 73%|#######2 | 455/625 [01:03<00:23, 7.09it/s]
reward: -1.8259, last reward: -0.0235, gradient norm: 1.304: 73%|#######2 | 456/625 [01:03<00:23, 7.10it/s]
reward: -1.8500, last reward: -0.0024, gradient norm: 1.416: 73%|#######2 | 456/625 [01:04<00:23, 7.10it/s]
reward: -1.8500, last reward: -0.0024, gradient norm: 1.416: 73%|#######3 | 457/625 [01:04<00:23, 7.11it/s]
reward: -1.9649, last reward: -0.4054, gradient norm: 39.3: 73%|#######3 | 457/625 [01:04<00:23, 7.11it/s]
reward: -1.9649, last reward: -0.4054, gradient norm: 39.3: 73%|#######3 | 458/625 [01:04<00:23, 7.11it/s]
reward: -2.2027, last reward: -0.0894, gradient norm: 4.275: 73%|#######3 | 458/625 [01:04<00:23, 7.11it/s]
reward: -2.2027, last reward: -0.0894, gradient norm: 4.275: 73%|#######3 | 459/625 [01:04<00:23, 7.09it/s]
reward: -1.5966, last reward: -0.0113, gradient norm: 1.368: 73%|#######3 | 459/625 [01:04<00:23, 7.09it/s]
reward: -1.5966, last reward: -0.0113, gradient norm: 1.368: 74%|#######3 | 460/625 [01:04<00:23, 7.10it/s]
reward: -1.6942, last reward: -0.0016, gradient norm: 0.4254: 74%|#######3 | 460/625 [01:04<00:23, 7.10it/s]
reward: -1.6942, last reward: -0.0016, gradient norm: 0.4254: 74%|#######3 | 461/625 [01:04<00:23, 7.09it/s]
reward: -1.6703, last reward: -0.0145, gradient norm: 2.142: 74%|#######3 | 461/625 [01:04<00:23, 7.09it/s]
reward: -1.6703, last reward: -0.0145, gradient norm: 2.142: 74%|#######3 | 462/625 [01:04<00:22, 7.10it/s]
reward: -1.8124, last reward: -0.0218, gradient norm: 0.9196: 74%|#######3 | 462/625 [01:04<00:22, 7.10it/s]
reward: -1.8124, last reward: -0.0218, gradient norm: 0.9196: 74%|#######4 | 463/625 [01:04<00:22, 7.11it/s]
reward: -1.8657, last reward: -0.0188, gradient norm: 0.8986: 74%|#######4 | 463/625 [01:05<00:22, 7.11it/s]
reward: -1.8657, last reward: -0.0188, gradient norm: 0.8986: 74%|#######4 | 464/625 [01:05<00:22, 7.12it/s]
reward: -2.0884, last reward: -0.0084, gradient norm: 0.5624: 74%|#######4 | 464/625 [01:05<00:22, 7.12it/s]
reward: -2.0884, last reward: -0.0084, gradient norm: 0.5624: 74%|#######4 | 465/625 [01:05<00:22, 7.14it/s]
reward: -1.8862, last reward: -0.0006, gradient norm: 0.5384: 74%|#######4 | 465/625 [01:05<00:22, 7.14it/s]
reward: -1.8862, last reward: -0.0006, gradient norm: 0.5384: 75%|#######4 | 466/625 [01:05<00:22, 7.14it/s]
reward: -2.1973, last reward: -0.0022, gradient norm: 0.5837: 75%|#######4 | 466/625 [01:05<00:22, 7.14it/s]
reward: -2.1973, last reward: -0.0022, gradient norm: 0.5837: 75%|#######4 | 467/625 [01:05<00:22, 7.15it/s]
reward: -1.8954, last reward: -0.0101, gradient norm: 0.6751: 75%|#######4 | 467/625 [01:05<00:22, 7.15it/s]
reward: -1.8954, last reward: -0.0101, gradient norm: 0.6751: 75%|#######4 | 468/625 [01:05<00:22, 7.10it/s]
reward: -1.8063, last reward: -0.0122, gradient norm: 0.9635: 75%|#######4 | 468/625 [01:05<00:22, 7.10it/s]
reward: -1.8063, last reward: -0.0122, gradient norm: 0.9635: 75%|#######5 | 469/625 [01:05<00:22, 7.08it/s]
reward: -2.0692, last reward: -0.0027, gradient norm: 0.4216: 75%|#######5 | 469/625 [01:05<00:22, 7.08it/s]
reward: -2.0692, last reward: -0.0027, gradient norm: 0.4216: 75%|#######5 | 470/625 [01:05<00:21, 7.07it/s]
reward: -2.1227, last reward: -0.0586, gradient norm: 3.162e+03: 75%|#######5 | 470/625 [01:06<00:21, 7.07it/s]
reward: -2.1227, last reward: -0.0586, gradient norm: 3.162e+03: 75%|#######5 | 471/625 [01:06<00:21, 7.08it/s]
reward: -1.9690, last reward: -0.0074, gradient norm: 0.4166: 75%|#######5 | 471/625 [01:06<00:21, 7.08it/s]
reward: -1.9690, last reward: -0.0074, gradient norm: 0.4166: 76%|#######5 | 472/625 [01:06<00:21, 7.10it/s]
reward: -2.6324, last reward: -0.0119, gradient norm: 1.345: 76%|#######5 | 472/625 [01:06<00:21, 7.10it/s]
reward: -2.6324, last reward: -0.0119, gradient norm: 1.345: 76%|#######5 | 473/625 [01:06<00:21, 7.10it/s]
reward: -2.0778, last reward: -0.0098, gradient norm: 1.166: 76%|#######5 | 473/625 [01:06<00:21, 7.10it/s]
reward: -2.0778, last reward: -0.0098, gradient norm: 1.166: 76%|#######5 | 474/625 [01:06<00:21, 7.12it/s]
reward: -1.8548, last reward: -0.0017, gradient norm: 0.4408: 76%|#######5 | 474/625 [01:06<00:21, 7.12it/s]
reward: -1.8548, last reward: -0.0017, gradient norm: 0.4408: 76%|#######6 | 475/625 [01:06<00:21, 7.12it/s]
reward: -1.8125, last reward: -0.0003, gradient norm: 0.1515: 76%|#######6 | 475/625 [01:06<00:21, 7.12it/s]
reward: -1.8125, last reward: -0.0003, gradient norm: 0.1515: 76%|#######6 | 476/625 [01:06<00:20, 7.15it/s]
reward: -2.2733, last reward: -0.0044, gradient norm: 0.2836: 76%|#######6 | 476/625 [01:06<00:20, 7.15it/s]
reward: -2.2733, last reward: -0.0044, gradient norm: 0.2836: 76%|#######6 | 477/625 [01:06<00:20, 7.17it/s]
reward: -1.7497, last reward: -0.0149, gradient norm: 0.7681: 76%|#######6 | 477/625 [01:07<00:20, 7.17it/s]
reward: -1.7497, last reward: -0.0149, gradient norm: 0.7681: 76%|#######6 | 478/625 [01:07<00:20, 7.19it/s]
reward: -1.8547, last reward: -0.0105, gradient norm: 0.7212: 76%|#######6 | 478/625 [01:07<00:20, 7.19it/s]
reward: -1.8547, last reward: -0.0105, gradient norm: 0.7212: 77%|#######6 | 479/625 [01:07<00:20, 7.20it/s]
reward: -1.9848, last reward: -0.0019, gradient norm: 0.6498: 77%|#######6 | 479/625 [01:07<00:20, 7.20it/s]
reward: -1.9848, last reward: -0.0019, gradient norm: 0.6498: 77%|#######6 | 480/625 [01:07<00:20, 7.20it/s]
reward: -2.1987, last reward: -0.0011, gradient norm: 0.5473: 77%|#######6 | 480/625 [01:07<00:20, 7.20it/s]
reward: -2.1987, last reward: -0.0011, gradient norm: 0.5473: 77%|#######6 | 481/625 [01:07<00:19, 7.20it/s]
reward: -1.8991, last reward: -0.0033, gradient norm: 0.6091: 77%|#######6 | 481/625 [01:07<00:19, 7.20it/s]
reward: -1.8991, last reward: -0.0033, gradient norm: 0.6091: 77%|#######7 | 482/625 [01:07<00:19, 7.21it/s]
reward: -1.9189, last reward: -0.0032, gradient norm: 0.5771: 77%|#######7 | 482/625 [01:07<00:19, 7.21it/s]
reward: -1.9189, last reward: -0.0032, gradient norm: 0.5771: 77%|#######7 | 483/625 [01:07<00:19, 7.18it/s]
reward: -1.6781, last reward: -0.0004, gradient norm: 0.7542: 77%|#######7 | 483/625 [01:07<00:19, 7.18it/s]
reward: -1.6781, last reward: -0.0004, gradient norm: 0.7542: 77%|#######7 | 484/625 [01:07<00:19, 7.19it/s]
reward: -1.5959, last reward: -0.0064, gradient norm: 0.4295: 77%|#######7 | 484/625 [01:08<00:19, 7.19it/s]
reward: -1.5959, last reward: -0.0064, gradient norm: 0.4295: 78%|#######7 | 485/625 [01:08<00:19, 7.18it/s]
reward: -2.2547, last reward: -0.0103, gradient norm: 0.4641: 78%|#######7 | 485/625 [01:08<00:19, 7.18it/s]
reward: -2.2547, last reward: -0.0103, gradient norm: 0.4641: 78%|#######7 | 486/625 [01:08<00:19, 7.17it/s]
reward: -2.1509, last reward: -0.0636, gradient norm: 6.547: 78%|#######7 | 486/625 [01:08<00:19, 7.17it/s]
reward: -2.1509, last reward: -0.0636, gradient norm: 6.547: 78%|#######7 | 487/625 [01:08<00:19, 7.16it/s]
reward: -2.0972, last reward: -0.0065, gradient norm: 0.2593: 78%|#######7 | 487/625 [01:08<00:19, 7.16it/s]
reward: -2.0972, last reward: -0.0065, gradient norm: 0.2593: 78%|#######8 | 488/625 [01:08<00:19, 7.16it/s]
reward: -2.1694, last reward: -0.0083, gradient norm: 0.5759: 78%|#######8 | 488/625 [01:08<00:19, 7.16it/s]
reward: -2.1694, last reward: -0.0083, gradient norm: 0.5759: 78%|#######8 | 489/625 [01:08<00:18, 7.17it/s]
reward: -2.0493, last reward: -0.0021, gradient norm: 0.7805: 78%|#######8 | 489/625 [01:08<00:18, 7.17it/s]
reward: -2.0493, last reward: -0.0021, gradient norm: 0.7805: 78%|#######8 | 490/625 [01:08<00:18, 7.16it/s]
reward: -2.0950, last reward: -0.0021, gradient norm: 0.497: 78%|#######8 | 490/625 [01:08<00:18, 7.16it/s]
reward: -2.0950, last reward: -0.0021, gradient norm: 0.497: 79%|#######8 | 491/625 [01:08<00:18, 7.17it/s]
reward: -1.9717, last reward: -0.0012, gradient norm: 0.3672: 79%|#######8 | 491/625 [01:08<00:18, 7.17it/s]
reward: -1.9717, last reward: -0.0012, gradient norm: 0.3672: 79%|#######8 | 492/625 [01:08<00:18, 7.18it/s]
reward: -2.0207, last reward: -0.0009, gradient norm: 0.331: 79%|#######8 | 492/625 [01:09<00:18, 7.18it/s]
reward: -2.0207, last reward: -0.0009, gradient norm: 0.331: 79%|#######8 | 493/625 [01:09<00:18, 7.19it/s]
reward: -1.8266, last reward: -0.0069, gradient norm: 0.5365: 79%|#######8 | 493/625 [01:09<00:18, 7.19it/s]
reward: -1.8266, last reward: -0.0069, gradient norm: 0.5365: 79%|#######9 | 494/625 [01:09<00:18, 7.17it/s]
reward: -2.2623, last reward: -0.0065, gradient norm: 0.5078: 79%|#######9 | 494/625 [01:09<00:18, 7.17it/s]
reward: -2.2623, last reward: -0.0065, gradient norm: 0.5078: 79%|#######9 | 495/625 [01:09<00:18, 7.16it/s]
reward: -2.0230, last reward: -0.0027, gradient norm: 0.4545: 79%|#######9 | 495/625 [01:09<00:18, 7.16it/s]
reward: -2.0230, last reward: -0.0027, gradient norm: 0.4545: 79%|#######9 | 496/625 [01:09<00:17, 7.17it/s]
reward: -1.6047, last reward: -0.0000, gradient norm: 0.09636: 79%|#######9 | 496/625 [01:09<00:17, 7.17it/s]
reward: -1.6047, last reward: -0.0000, gradient norm: 0.09636: 80%|#######9 | 497/625 [01:09<00:17, 7.17it/s]
reward: -1.8754, last reward: -0.0010, gradient norm: 0.2: 80%|#######9 | 497/625 [01:09<00:17, 7.17it/s]
reward: -1.8754, last reward: -0.0010, gradient norm: 0.2: 80%|#######9 | 498/625 [01:09<00:17, 7.17it/s]
reward: -2.6216, last reward: -0.0031, gradient norm: 0.8269: 80%|#######9 | 498/625 [01:09<00:17, 7.17it/s]
reward: -2.6216, last reward: -0.0031, gradient norm: 0.8269: 80%|#######9 | 499/625 [01:09<00:17, 7.18it/s]
reward: -1.7361, last reward: -0.0023, gradient norm: 0.4082: 80%|#######9 | 499/625 [01:10<00:17, 7.18it/s]
reward: -1.7361, last reward: -0.0023, gradient norm: 0.4082: 80%|######## | 500/625 [01:10<00:17, 7.19it/s]
reward: -1.6642, last reward: -0.0006, gradient norm: 0.2284: 80%|######## | 500/625 [01:10<00:17, 7.19it/s]
reward: -1.6642, last reward: -0.0006, gradient norm: 0.2284: 80%|######## | 501/625 [01:10<00:17, 7.18it/s]
reward: -1.9130, last reward: -0.0008, gradient norm: 0.3031: 80%|######## | 501/625 [01:10<00:17, 7.18it/s]
reward: -1.9130, last reward: -0.0008, gradient norm: 0.3031: 80%|######## | 502/625 [01:10<00:17, 7.19it/s]
reward: -2.2944, last reward: -0.0035, gradient norm: 0.2986: 80%|######## | 502/625 [01:10<00:17, 7.19it/s]
reward: -2.2944, last reward: -0.0035, gradient norm: 0.2986: 80%|######## | 503/625 [01:10<00:16, 7.19it/s]
reward: -1.7624, last reward: -0.0056, gradient norm: 0.3858: 80%|######## | 503/625 [01:10<00:16, 7.19it/s]
reward: -1.7624, last reward: -0.0056, gradient norm: 0.3858: 81%|######## | 504/625 [01:10<00:16, 7.19it/s]
reward: -2.0890, last reward: -0.0042, gradient norm: 0.38: 81%|######## | 504/625 [01:10<00:16, 7.19it/s]
reward: -2.0890, last reward: -0.0042, gradient norm: 0.38: 81%|######## | 505/625 [01:10<00:16, 7.19it/s]
reward: -1.7505, last reward: -0.0017, gradient norm: 0.2157: 81%|######## | 505/625 [01:10<00:16, 7.19it/s]
reward: -1.7505, last reward: -0.0017, gradient norm: 0.2157: 81%|######## | 506/625 [01:10<00:16, 7.19it/s]
reward: -1.8394, last reward: -0.0013, gradient norm: 0.3413: 81%|######## | 506/625 [01:11<00:16, 7.19it/s]
reward: -1.8394, last reward: -0.0013, gradient norm: 0.3413: 81%|########1 | 507/625 [01:11<00:16, 7.19it/s]
reward: -1.9609, last reward: -0.0041, gradient norm: 0.6905: 81%|########1 | 507/625 [01:11<00:16, 7.19it/s]
reward: -1.9609, last reward: -0.0041, gradient norm: 0.6905: 81%|########1 | 508/625 [01:11<00:16, 7.16it/s]
reward: -1.8467, last reward: -0.0011, gradient norm: 0.4409: 81%|########1 | 508/625 [01:11<00:16, 7.16it/s]
reward: -1.8467, last reward: -0.0011, gradient norm: 0.4409: 81%|########1 | 509/625 [01:11<00:16, 7.16it/s]
reward: -2.0252, last reward: -0.0021, gradient norm: 0.213: 81%|########1 | 509/625 [01:11<00:16, 7.16it/s]
reward: -2.0252, last reward: -0.0021, gradient norm: 0.213: 82%|########1 | 510/625 [01:11<00:16, 7.16it/s]
reward: -1.8128, last reward: -0.0073, gradient norm: 0.3559: 82%|########1 | 510/625 [01:11<00:16, 7.16it/s]
reward: -1.8128, last reward: -0.0073, gradient norm: 0.3559: 82%|########1 | 511/625 [01:11<00:15, 7.16it/s]
reward: -2.1479, last reward: -0.0264, gradient norm: 3.68: 82%|########1 | 511/625 [01:11<00:15, 7.16it/s]
reward: -2.1479, last reward: -0.0264, gradient norm: 3.68: 82%|########1 | 512/625 [01:11<00:15, 7.16it/s]
reward: -2.1589, last reward: -0.0025, gradient norm: 5.566: 82%|########1 | 512/625 [01:11<00:15, 7.16it/s]
reward: -2.1589, last reward: -0.0025, gradient norm: 5.566: 82%|########2 | 513/625 [01:11<00:15, 7.17it/s]
reward: -2.2756, last reward: -0.0046, gradient norm: 0.5266: 82%|########2 | 513/625 [01:12<00:15, 7.17it/s]
reward: -2.2756, last reward: -0.0046, gradient norm: 0.5266: 82%|########2 | 514/625 [01:12<00:15, 7.16it/s]
reward: -1.9873, last reward: -0.0112, gradient norm: 0.9314: 82%|########2 | 514/625 [01:12<00:15, 7.16it/s]
reward: -1.9873, last reward: -0.0112, gradient norm: 0.9314: 82%|########2 | 515/625 [01:12<00:15, 7.15it/s]
reward: -2.3791, last reward: -0.0721, gradient norm: 1.14: 82%|########2 | 515/625 [01:12<00:15, 7.15it/s]
reward: -2.3791, last reward: -0.0721, gradient norm: 1.14: 83%|########2 | 516/625 [01:12<00:15, 7.16it/s]
reward: -2.4580, last reward: -0.0758, gradient norm: 0.6114: 83%|########2 | 516/625 [01:12<00:15, 7.16it/s]
reward: -2.4580, last reward: -0.0758, gradient norm: 0.6114: 83%|########2 | 517/625 [01:12<00:15, 7.17it/s]
reward: -1.9748, last reward: -0.0001, gradient norm: 0.2431: 83%|########2 | 517/625 [01:12<00:15, 7.17it/s]
reward: -1.9748, last reward: -0.0001, gradient norm: 0.2431: 83%|########2 | 518/625 [01:12<00:14, 7.17it/s]
reward: -2.1958, last reward: -0.0044, gradient norm: 0.5553: 83%|########2 | 518/625 [01:12<00:14, 7.17it/s]
reward: -2.1958, last reward: -0.0044, gradient norm: 0.5553: 83%|########3 | 519/625 [01:12<00:14, 7.17it/s]
reward: -1.8924, last reward: -0.0097, gradient norm: 17.34: 83%|########3 | 519/625 [01:12<00:14, 7.17it/s]
reward: -1.8924, last reward: -0.0097, gradient norm: 17.34: 83%|########3 | 520/625 [01:12<00:14, 7.17it/s]
reward: -2.3737, last reward: -0.0234, gradient norm: 1.899: 83%|########3 | 520/625 [01:13<00:14, 7.17it/s]
reward: -2.3737, last reward: -0.0234, gradient norm: 1.899: 83%|########3 | 521/625 [01:13<00:14, 7.17it/s]
reward: -1.9125, last reward: -0.0063, gradient norm: 0.4623: 83%|########3 | 521/625 [01:13<00:14, 7.17it/s]
reward: -1.9125, last reward: -0.0063, gradient norm: 0.4623: 84%|########3 | 522/625 [01:13<00:14, 7.15it/s]
reward: -2.3230, last reward: -0.0589, gradient norm: 0.3784: 84%|########3 | 522/625 [01:13<00:14, 7.15it/s]
reward: -2.3230, last reward: -0.0589, gradient norm: 0.3784: 84%|########3 | 523/625 [01:13<00:14, 7.14it/s]
reward: -1.9482, last reward: -0.0051, gradient norm: 1.105: 84%|########3 | 523/625 [01:13<00:14, 7.14it/s]
reward: -1.9482, last reward: -0.0051, gradient norm: 1.105: 84%|########3 | 524/625 [01:13<00:14, 7.15it/s]
reward: -2.1979, last reward: -0.0045, gradient norm: 0.6401: 84%|########3 | 524/625 [01:13<00:14, 7.15it/s]
reward: -2.1979, last reward: -0.0045, gradient norm: 0.6401: 84%|########4 | 525/625 [01:13<00:13, 7.15it/s]
reward: -2.1588, last reward: -0.0048, gradient norm: 0.6255: 84%|########4 | 525/625 [01:13<00:13, 7.15it/s]
reward: -2.1588, last reward: -0.0048, gradient norm: 0.6255: 84%|########4 | 526/625 [01:13<00:13, 7.14it/s]
reward: -1.6084, last reward: -0.0010, gradient norm: 0.3477: 84%|########4 | 526/625 [01:13<00:13, 7.14it/s]
reward: -1.6084, last reward: -0.0010, gradient norm: 0.3477: 84%|########4 | 527/625 [01:13<00:13, 7.14it/s]
reward: -2.1475, last reward: -0.0209, gradient norm: 0.3456: 84%|########4 | 527/625 [01:14<00:13, 7.14it/s]
reward: -2.1475, last reward: -0.0209, gradient norm: 0.3456: 84%|########4 | 528/625 [01:14<00:13, 7.15it/s]
reward: -1.7611, last reward: -0.1040, gradient norm: 18.52: 84%|########4 | 528/625 [01:14<00:13, 7.15it/s]
reward: -1.7611, last reward: -0.1040, gradient norm: 18.52: 85%|########4 | 529/625 [01:14<00:13, 7.16it/s]
reward: -2.0099, last reward: -0.0173, gradient norm: 1.643: 85%|########4 | 529/625 [01:14<00:13, 7.16it/s]
reward: -2.0099, last reward: -0.0173, gradient norm: 1.643: 85%|########4 | 530/625 [01:14<00:13, 7.16it/s]
reward: -2.8189, last reward: -1.4358, gradient norm: 46.61: 85%|########4 | 530/625 [01:14<00:13, 7.16it/s]
reward: -2.8189, last reward: -1.4358, gradient norm: 46.61: 85%|########4 | 531/625 [01:14<00:13, 7.15it/s]
reward: -2.9897, last reward: -2.4869, gradient norm: 51.23: 85%|########4 | 531/625 [01:14<00:13, 7.15it/s]
reward: -2.9897, last reward: -2.4869, gradient norm: 51.23: 85%|########5 | 532/625 [01:14<00:13, 7.09it/s]
reward: -2.1548, last reward: -0.9751, gradient norm: 72.21: 85%|########5 | 532/625 [01:14<00:13, 7.09it/s]
reward: -2.1548, last reward: -0.9751, gradient norm: 72.21: 85%|########5 | 533/625 [01:14<00:12, 7.09it/s]
reward: -1.6362, last reward: -0.0022, gradient norm: 0.7495: 85%|########5 | 533/625 [01:14<00:12, 7.09it/s]
reward: -1.6362, last reward: -0.0022, gradient norm: 0.7495: 85%|########5 | 534/625 [01:14<00:12, 7.09it/s]
reward: -2.1749, last reward: -0.0105, gradient norm: 0.9513: 85%|########5 | 534/625 [01:14<00:12, 7.09it/s]
reward: -2.1749, last reward: -0.0105, gradient norm: 0.9513: 86%|########5 | 535/625 [01:14<00:12, 7.07it/s]
reward: -1.7708, last reward: -0.0371, gradient norm: 1.432: 86%|########5 | 535/625 [01:15<00:12, 7.07it/s]
reward: -1.7708, last reward: -0.0371, gradient norm: 1.432: 86%|########5 | 536/625 [01:15<00:12, 7.08it/s]
reward: -2.2649, last reward: -0.0437, gradient norm: 2.327: 86%|########5 | 536/625 [01:15<00:12, 7.08it/s]
reward: -2.2649, last reward: -0.0437, gradient norm: 2.327: 86%|########5 | 537/625 [01:15<00:12, 7.07it/s]
reward: -2.5491, last reward: -0.0276, gradient norm: 1.246: 86%|########5 | 537/625 [01:15<00:12, 7.07it/s]
reward: -2.5491, last reward: -0.0276, gradient norm: 1.246: 86%|########6 | 538/625 [01:15<00:12, 7.08it/s]
reward: -2.6426, last reward: -0.7294, gradient norm: 1.078e+03: 86%|########6 | 538/625 [01:15<00:12, 7.08it/s]
reward: -2.6426, last reward: -0.7294, gradient norm: 1.078e+03: 86%|########6 | 539/625 [01:15<00:12, 7.08it/s]
reward: -1.9928, last reward: -0.0003, gradient norm: 1.576: 86%|########6 | 539/625 [01:15<00:12, 7.08it/s]
reward: -1.9928, last reward: -0.0003, gradient norm: 1.576: 86%|########6 | 540/625 [01:15<00:12, 7.08it/s]
reward: -1.7937, last reward: -0.0124, gradient norm: 0.9664: 86%|########6 | 540/625 [01:15<00:12, 7.08it/s]
reward: -1.7937, last reward: -0.0124, gradient norm: 0.9664: 87%|########6 | 541/625 [01:15<00:11, 7.08it/s]
reward: -2.3342, last reward: -0.0204, gradient norm: 1.81: 87%|########6 | 541/625 [01:15<00:11, 7.08it/s]
reward: -2.3342, last reward: -0.0204, gradient norm: 1.81: 87%|########6 | 542/625 [01:15<00:11, 7.08it/s]
reward: -2.2046, last reward: -0.0122, gradient norm: 1.004: 87%|########6 | 542/625 [01:16<00:11, 7.08it/s]
reward: -2.2046, last reward: -0.0122, gradient norm: 1.004: 87%|########6 | 543/625 [01:16<00:11, 7.10it/s]
reward: -2.0000, last reward: -0.0014, gradient norm: 0.5496: 87%|########6 | 543/625 [01:16<00:11, 7.10it/s]
reward: -2.0000, last reward: -0.0014, gradient norm: 0.5496: 87%|########7 | 544/625 [01:16<00:11, 7.10it/s]
reward: -2.0956, last reward: -0.0059, gradient norm: 1.425: 87%|########7 | 544/625 [01:16<00:11, 7.10it/s]
reward: -2.0956, last reward: -0.0059, gradient norm: 1.425: 87%|########7 | 545/625 [01:16<00:11, 7.12it/s]
reward: -2.9028, last reward: -0.5843, gradient norm: 21.12: 87%|########7 | 545/625 [01:16<00:11, 7.12it/s]
reward: -2.9028, last reward: -0.5843, gradient norm: 21.12: 87%|########7 | 546/625 [01:16<00:11, 7.11it/s]
reward: -2.0674, last reward: -0.0178, gradient norm: 0.797: 87%|########7 | 546/625 [01:16<00:11, 7.11it/s]
reward: -2.0674, last reward: -0.0178, gradient norm: 0.797: 88%|########7 | 547/625 [01:16<00:10, 7.11it/s]
reward: -2.2815, last reward: -0.0599, gradient norm: 1.227: 88%|########7 | 547/625 [01:16<00:10, 7.11it/s]
reward: -2.2815, last reward: -0.0599, gradient norm: 1.227: 88%|########7 | 548/625 [01:16<00:10, 7.14it/s]
reward: -3.1587, last reward: -0.9276, gradient norm: 20.56: 88%|########7 | 548/625 [01:16<00:10, 7.14it/s]
reward: -3.1587, last reward: -0.9276, gradient norm: 20.56: 88%|########7 | 549/625 [01:16<00:10, 7.17it/s]
reward: -3.8228, last reward: -2.9229, gradient norm: 308.2: 88%|########7 | 549/625 [01:17<00:10, 7.17it/s]
reward: -3.8228, last reward: -2.9229, gradient norm: 308.2: 88%|########8 | 550/625 [01:17<00:10, 7.18it/s]
reward: -1.6164, last reward: -0.0120, gradient norm: 2.259: 88%|########8 | 550/625 [01:17<00:10, 7.18it/s]
reward: -1.6164, last reward: -0.0120, gradient norm: 2.259: 88%|########8 | 551/625 [01:17<00:10, 7.17it/s]
reward: -1.6850, last reward: -0.0227, gradient norm: 0.9167: 88%|########8 | 551/625 [01:17<00:10, 7.17it/s]
reward: -1.6850, last reward: -0.0227, gradient norm: 0.9167: 88%|########8 | 552/625 [01:17<00:10, 7.17it/s]
reward: -2.3092, last reward: -0.0670, gradient norm: 0.9177: 88%|########8 | 552/625 [01:17<00:10, 7.17it/s]
reward: -2.3092, last reward: -0.0670, gradient norm: 0.9177: 88%|########8 | 553/625 [01:17<00:10, 7.19it/s]
reward: -2.1599, last reward: -0.0043, gradient norm: 1.195: 88%|########8 | 553/625 [01:17<00:10, 7.19it/s]
reward: -2.1599, last reward: -0.0043, gradient norm: 1.195: 89%|########8 | 554/625 [01:17<00:09, 7.16it/s]
reward: -2.4672, last reward: -0.0057, gradient norm: 0.6367: 89%|########8 | 554/625 [01:17<00:09, 7.16it/s]
reward: -2.4672, last reward: -0.0057, gradient norm: 0.6367: 89%|########8 | 555/625 [01:17<00:09, 7.14it/s]
reward: -2.3657, last reward: -0.1970, gradient norm: 4.202: 89%|########8 | 555/625 [01:17<00:09, 7.14it/s]
reward: -2.3657, last reward: -0.1970, gradient norm: 4.202: 89%|########8 | 556/625 [01:17<00:09, 7.16it/s]
reward: -2.6694, last reward: -0.1215, gradient norm: 1.324: 89%|########8 | 556/625 [01:18<00:09, 7.16it/s]
reward: -2.6694, last reward: -0.1215, gradient norm: 1.324: 89%|########9 | 557/625 [01:18<00:09, 7.17it/s]
reward: -2.2622, last reward: -0.0372, gradient norm: 0.4841: 89%|########9 | 557/625 [01:18<00:09, 7.17it/s]
reward: -2.2622, last reward: -0.0372, gradient norm: 0.4841: 89%|########9 | 558/625 [01:18<00:09, 7.11it/s]
reward: -2.2707, last reward: -0.0058, gradient norm: 5.757: 89%|########9 | 558/625 [01:18<00:09, 7.11it/s]
reward: -2.2707, last reward: -0.0058, gradient norm: 5.757: 89%|########9 | 559/625 [01:18<00:09, 7.09it/s]
reward: -2.2267, last reward: -0.0014, gradient norm: 0.5415: 89%|########9 | 559/625 [01:18<00:09, 7.09it/s]
reward: -2.2267, last reward: -0.0014, gradient norm: 0.5415: 90%|########9 | 560/625 [01:18<00:09, 7.08it/s]
reward: -2.4556, last reward: -0.0163, gradient norm: 1.146: 90%|########9 | 560/625 [01:18<00:09, 7.08it/s]
reward: -2.4556, last reward: -0.0163, gradient norm: 1.146: 90%|########9 | 561/625 [01:18<00:09, 7.06it/s]
reward: -2.1839, last reward: -0.0809, gradient norm: 0.6262: 90%|########9 | 561/625 [01:18<00:09, 7.06it/s]
reward: -2.1839, last reward: -0.0809, gradient norm: 0.6262: 90%|########9 | 562/625 [01:18<00:08, 7.05it/s]
reward: -2.0278, last reward: -0.0018, gradient norm: 1.327: 90%|########9 | 562/625 [01:18<00:08, 7.05it/s]
reward: -2.0278, last reward: -0.0018, gradient norm: 1.327: 90%|######### | 563/625 [01:18<00:08, 7.02it/s]
reward: -2.1112, last reward: -0.0011, gradient norm: 0.354: 90%|######### | 563/625 [01:19<00:08, 7.02it/s]
reward: -2.1112, last reward: -0.0011, gradient norm: 0.354: 90%|######### | 564/625 [01:19<00:08, 7.03it/s]
reward: -2.6155, last reward: -0.0004, gradient norm: 2.008: 90%|######### | 564/625 [01:19<00:08, 7.03it/s]
reward: -2.6155, last reward: -0.0004, gradient norm: 2.008: 90%|######### | 565/625 [01:19<00:08, 7.04it/s]
reward: -3.1427, last reward: -0.3582, gradient norm: 7.624: 90%|######### | 565/625 [01:19<00:08, 7.04it/s]
reward: -3.1427, last reward: -0.3582, gradient norm: 7.624: 91%|######### | 566/625 [01:19<00:08, 7.07it/s]
reward: -2.7870, last reward: -0.9490, gradient norm: 18.26: 91%|######### | 566/625 [01:19<00:08, 7.07it/s]
reward: -2.7870, last reward: -0.9490, gradient norm: 18.26: 91%|######### | 567/625 [01:19<00:08, 7.07it/s]
reward: -3.0439, last reward: -0.8796, gradient norm: 29.89: 91%|######### | 567/625 [01:19<00:08, 7.07it/s]
reward: -3.0439, last reward: -0.8796, gradient norm: 29.89: 91%|######### | 568/625 [01:19<00:08, 7.06it/s]
reward: -2.8026, last reward: -0.2720, gradient norm: 8.612: 91%|######### | 568/625 [01:19<00:08, 7.06it/s]
reward: -2.8026, last reward: -0.2720, gradient norm: 8.612: 91%|#########1| 569/625 [01:19<00:07, 7.06it/s]
reward: -2.3147, last reward: -0.8486, gradient norm: 41.13: 91%|#########1| 569/625 [01:19<00:07, 7.06it/s]
reward: -2.3147, last reward: -0.8486, gradient norm: 41.13: 91%|#########1| 570/625 [01:19<00:07, 7.08it/s]
reward: -1.7917, last reward: -0.0129, gradient norm: 2.365: 91%|#########1| 570/625 [01:20<00:07, 7.08it/s]
reward: -1.7917, last reward: -0.0129, gradient norm: 2.365: 91%|#########1| 571/625 [01:20<00:07, 7.11it/s]
reward: -1.9553, last reward: -0.0020, gradient norm: 0.6871: 91%|#########1| 571/625 [01:20<00:07, 7.11it/s]
reward: -1.9553, last reward: -0.0020, gradient norm: 0.6871: 92%|#########1| 572/625 [01:20<00:07, 7.10it/s]
reward: -2.3132, last reward: -0.0159, gradient norm: 0.8646: 92%|#########1| 572/625 [01:20<00:07, 7.10it/s]
reward: -2.3132, last reward: -0.0159, gradient norm: 0.8646: 92%|#########1| 573/625 [01:20<00:07, 7.12it/s]
reward: -1.5320, last reward: -0.0269, gradient norm: 1.02: 92%|#########1| 573/625 [01:20<00:07, 7.12it/s]
reward: -1.5320, last reward: -0.0269, gradient norm: 1.02: 92%|#########1| 574/625 [01:20<00:07, 7.15it/s]
reward: -2.2955, last reward: -0.0245, gradient norm: 1.267: 92%|#########1| 574/625 [01:20<00:07, 7.15it/s]
reward: -2.2955, last reward: -0.0245, gradient norm: 1.267: 92%|#########2| 575/625 [01:20<00:07, 7.14it/s]
reward: -2.3347, last reward: -0.0179, gradient norm: 1.528: 92%|#########2| 575/625 [01:20<00:07, 7.14it/s]
reward: -2.3347, last reward: -0.0179, gradient norm: 1.528: 92%|#########2| 576/625 [01:20<00:06, 7.12it/s]
reward: -1.9718, last reward: -0.1629, gradient norm: 8.804: 92%|#########2| 576/625 [01:20<00:06, 7.12it/s]
reward: -1.9718, last reward: -0.1629, gradient norm: 8.804: 92%|#########2| 577/625 [01:20<00:06, 7.10it/s]
reward: -2.4164, last reward: -0.0070, gradient norm: 0.4335: 92%|#########2| 577/625 [01:21<00:06, 7.10it/s]
reward: -2.4164, last reward: -0.0070, gradient norm: 0.4335: 92%|#########2| 578/625 [01:21<00:06, 7.12it/s]
reward: -2.2993, last reward: -0.0011, gradient norm: 1.371: 92%|#########2| 578/625 [01:21<00:06, 7.12it/s]
reward: -2.2993, last reward: -0.0011, gradient norm: 1.371: 93%|#########2| 579/625 [01:21<00:06, 7.12it/s]
reward: -3.3049, last reward: -0.9063, gradient norm: 34.23: 93%|#########2| 579/625 [01:21<00:06, 7.12it/s]
reward: -3.3049, last reward: -0.9063, gradient norm: 34.23: 93%|#########2| 580/625 [01:21<00:06, 7.14it/s]
reward: -2.8785, last reward: -0.3295, gradient norm: 10.91: 93%|#########2| 580/625 [01:21<00:06, 7.14it/s]
reward: -2.8785, last reward: -0.3295, gradient norm: 10.91: 93%|#########2| 581/625 [01:21<00:06, 7.15it/s]
reward: -2.5184, last reward: -0.0546, gradient norm: 21.09: 93%|#########2| 581/625 [01:21<00:06, 7.15it/s]
reward: -2.5184, last reward: -0.0546, gradient norm: 21.09: 93%|#########3| 582/625 [01:21<00:06, 7.15it/s]
reward: -2.4039, last reward: -0.4589, gradient norm: 10.86: 93%|#########3| 582/625 [01:21<00:06, 7.15it/s]
reward: -2.4039, last reward: -0.4589, gradient norm: 10.86: 93%|#########3| 583/625 [01:21<00:05, 7.12it/s]
reward: -2.4697, last reward: -0.2476, gradient norm: 4.689: 93%|#########3| 583/625 [01:21<00:05, 7.12it/s]
reward: -2.4697, last reward: -0.2476, gradient norm: 4.689: 93%|#########3| 584/625 [01:21<00:05, 7.13it/s]
reward: -2.0018, last reward: -0.2397, gradient norm: 8.393: 93%|#########3| 584/625 [01:22<00:05, 7.13it/s]
reward: -2.0018, last reward: -0.2397, gradient norm: 8.393: 94%|#########3| 585/625 [01:22<00:05, 7.11it/s]
reward: -2.4953, last reward: -0.1775, gradient norm: 24.17: 94%|#########3| 585/625 [01:22<00:05, 7.11it/s]
reward: -2.4953, last reward: -0.1775, gradient norm: 24.17: 94%|#########3| 586/625 [01:22<00:05, 7.11it/s]
reward: -2.2258, last reward: -0.0110, gradient norm: 0.7671: 94%|#########3| 586/625 [01:22<00:05, 7.11it/s]
reward: -2.2258, last reward: -0.0110, gradient norm: 0.7671: 94%|#########3| 587/625 [01:22<00:05, 7.09it/s]
reward: -2.3981, last reward: -0.0011, gradient norm: 1.617: 94%|#########3| 587/625 [01:22<00:05, 7.09it/s]
reward: -2.3981, last reward: -0.0011, gradient norm: 1.617: 94%|#########4| 588/625 [01:22<00:05, 7.08it/s]
reward: -1.8590, last reward: -0.0007, gradient norm: 1.131: 94%|#########4| 588/625 [01:22<00:05, 7.08it/s]
reward: -1.8590, last reward: -0.0007, gradient norm: 1.131: 94%|#########4| 589/625 [01:22<00:05, 7.07it/s]
reward: -1.9820, last reward: -0.4221, gradient norm: 49.4: 94%|#########4| 589/625 [01:22<00:05, 7.07it/s]
reward: -1.9820, last reward: -0.4221, gradient norm: 49.4: 94%|#########4| 590/625 [01:22<00:04, 7.06it/s]
reward: -2.1293, last reward: -0.0116, gradient norm: 0.868: 94%|#########4| 590/625 [01:22<00:04, 7.06it/s]
reward: -2.1293, last reward: -0.0116, gradient norm: 0.868: 95%|#########4| 591/625 [01:22<00:04, 7.08it/s]
reward: -2.1675, last reward: -0.0173, gradient norm: 0.5931: 95%|#########4| 591/625 [01:23<00:04, 7.08it/s]
reward: -2.1675, last reward: -0.0173, gradient norm: 0.5931: 95%|#########4| 592/625 [01:23<00:04, 7.09it/s]
reward: -2.2910, last reward: -0.0207, gradient norm: 0.5219: 95%|#########4| 592/625 [01:23<00:04, 7.09it/s]
reward: -2.2910, last reward: -0.0207, gradient norm: 0.5219: 95%|#########4| 593/625 [01:23<00:04, 7.08it/s]
reward: -2.2124, last reward: -0.1730, gradient norm: 5.737: 95%|#########4| 593/625 [01:23<00:04, 7.08it/s]
reward: -2.2124, last reward: -0.1730, gradient norm: 5.737: 95%|#########5| 594/625 [01:23<00:04, 7.10it/s]
reward: -2.2914, last reward: -0.0206, gradient norm: 0.485: 95%|#########5| 594/625 [01:23<00:04, 7.10it/s]
reward: -2.2914, last reward: -0.0206, gradient norm: 0.485: 95%|#########5| 595/625 [01:23<00:04, 7.12it/s]
reward: -2.0890, last reward: -0.0172, gradient norm: 0.3982: 95%|#########5| 595/625 [01:23<00:04, 7.12it/s]
reward: -2.0890, last reward: -0.0172, gradient norm: 0.3982: 95%|#########5| 596/625 [01:23<00:04, 7.14it/s]
reward: -2.0945, last reward: -0.0121, gradient norm: 0.4789: 95%|#########5| 596/625 [01:23<00:04, 7.14it/s]
reward: -2.0945, last reward: -0.0121, gradient norm: 0.4789: 96%|#########5| 597/625 [01:23<00:03, 7.14it/s]
reward: -2.3805, last reward: -0.0069, gradient norm: 0.4074: 96%|#########5| 597/625 [01:23<00:03, 7.14it/s]
reward: -2.3805, last reward: -0.0069, gradient norm: 0.4074: 96%|#########5| 598/625 [01:23<00:03, 7.16it/s]
reward: -2.3310, last reward: -0.0031, gradient norm: 0.5065: 96%|#########5| 598/625 [01:23<00:03, 7.16it/s]
reward: -2.3310, last reward: -0.0031, gradient norm: 0.5065: 96%|#########5| 599/625 [01:23<00:03, 7.15it/s]
reward: -2.6028, last reward: -0.0006, gradient norm: 0.6316: 96%|#########5| 599/625 [01:24<00:03, 7.15it/s]
reward: -2.6028, last reward: -0.0006, gradient norm: 0.6316: 96%|#########6| 600/625 [01:24<00:03, 7.16it/s]
reward: -2.6724, last reward: -0.0001, gradient norm: 0.6523: 96%|#########6| 600/625 [01:24<00:03, 7.16it/s]
reward: -2.6724, last reward: -0.0001, gradient norm: 0.6523: 96%|#########6| 601/625 [01:24<00:03, 7.18it/s]
reward: -2.2481, last reward: -0.0136, gradient norm: 0.4298: 96%|#########6| 601/625 [01:24<00:03, 7.18it/s]
reward: -2.2481, last reward: -0.0136, gradient norm: 0.4298: 96%|#########6| 602/625 [01:24<00:03, 7.20it/s]
reward: -2.3524, last reward: -0.0043, gradient norm: 0.2629: 96%|#########6| 602/625 [01:24<00:03, 7.20it/s]
reward: -2.3524, last reward: -0.0043, gradient norm: 0.2629: 96%|#########6| 603/625 [01:24<00:03, 7.18it/s]
reward: -2.2635, last reward: -0.0069, gradient norm: 0.7839: 96%|#########6| 603/625 [01:24<00:03, 7.18it/s]
reward: -2.2635, last reward: -0.0069, gradient norm: 0.7839: 97%|#########6| 604/625 [01:24<00:02, 7.14it/s]
reward: -2.6041, last reward: -0.8027, gradient norm: 11.7: 97%|#########6| 604/625 [01:24<00:02, 7.14it/s]
reward: -2.6041, last reward: -0.8027, gradient norm: 11.7: 97%|#########6| 605/625 [01:24<00:02, 7.12it/s]
reward: -4.4170, last reward: -3.4675, gradient norm: 60.04: 97%|#########6| 605/625 [01:24<00:02, 7.12it/s]
reward: -4.4170, last reward: -3.4675, gradient norm: 60.04: 97%|#########6| 606/625 [01:24<00:02, 7.11it/s]
reward: -4.3153, last reward: -2.9316, gradient norm: 53.11: 97%|#########6| 606/625 [01:25<00:02, 7.11it/s]
reward: -4.3153, last reward: -2.9316, gradient norm: 53.11: 97%|#########7| 607/625 [01:25<00:02, 7.10it/s]
reward: -3.0649, last reward: -0.9722, gradient norm: 30.84: 97%|#########7| 607/625 [01:25<00:02, 7.10it/s]
reward: -3.0649, last reward: -0.9722, gradient norm: 30.84: 97%|#########7| 608/625 [01:25<00:02, 7.10it/s]
reward: -2.7989, last reward: -0.0329, gradient norm: 1.261: 97%|#########7| 608/625 [01:25<00:02, 7.10it/s]
reward: -2.7989, last reward: -0.0329, gradient norm: 1.261: 97%|#########7| 609/625 [01:25<00:02, 7.09it/s]
reward: -2.1976, last reward: -0.6852, gradient norm: 20.33: 97%|#########7| 609/625 [01:25<00:02, 7.09it/s]
reward: -2.1976, last reward: -0.6852, gradient norm: 20.33: 98%|#########7| 610/625 [01:25<00:02, 7.10it/s]
reward: -2.4793, last reward: -0.1255, gradient norm: 14.69: 98%|#########7| 610/625 [01:25<00:02, 7.10it/s]
reward: -2.4793, last reward: -0.1255, gradient norm: 14.69: 98%|#########7| 611/625 [01:25<00:01, 7.10it/s]
reward: -2.4581, last reward: -0.0394, gradient norm: 2.429: 98%|#########7| 611/625 [01:25<00:01, 7.10it/s]
reward: -2.4581, last reward: -0.0394, gradient norm: 2.429: 98%|#########7| 612/625 [01:25<00:01, 7.11it/s]
reward: -2.2047, last reward: -0.0326, gradient norm: 1.147: 98%|#########7| 612/625 [01:25<00:01, 7.11it/s]
reward: -2.2047, last reward: -0.0326, gradient norm: 1.147: 98%|#########8| 613/625 [01:25<00:01, 7.09it/s]
reward: -1.8967, last reward: -0.0129, gradient norm: 0.8619: 98%|#########8| 613/625 [01:26<00:01, 7.09it/s]
reward: -1.8967, last reward: -0.0129, gradient norm: 0.8619: 98%|#########8| 614/625 [01:26<00:01, 7.10it/s]
reward: -2.5906, last reward: -0.0015, gradient norm: 0.6491: 98%|#########8| 614/625 [01:26<00:01, 7.10it/s]
reward: -2.5906, last reward: -0.0015, gradient norm: 0.6491: 98%|#########8| 615/625 [01:26<00:01, 7.09it/s]
reward: -1.6634, last reward: -0.0007, gradient norm: 0.4394: 98%|#########8| 615/625 [01:26<00:01, 7.09it/s]
reward: -1.6634, last reward: -0.0007, gradient norm: 0.4394: 99%|#########8| 616/625 [01:26<00:01, 7.11it/s]
reward: -2.0624, last reward: -0.0061, gradient norm: 0.5676: 99%|#########8| 616/625 [01:26<00:01, 7.11it/s]
reward: -2.0624, last reward: -0.0061, gradient norm: 0.5676: 99%|#########8| 617/625 [01:26<00:01, 7.10it/s]
reward: -2.3259, last reward: -0.0131, gradient norm: 0.7733: 99%|#########8| 617/625 [01:26<00:01, 7.10it/s]
reward: -2.3259, last reward: -0.0131, gradient norm: 0.7733: 99%|#########8| 618/625 [01:26<00:00, 7.09it/s]
reward: -1.7515, last reward: -0.0189, gradient norm: 0.5575: 99%|#########8| 618/625 [01:26<00:00, 7.09it/s]
reward: -1.7515, last reward: -0.0189, gradient norm: 0.5575: 99%|#########9| 619/625 [01:26<00:00, 7.10it/s]
reward: -1.9313, last reward: -0.0207, gradient norm: 0.6286: 99%|#########9| 619/625 [01:26<00:00, 7.10it/s]
reward: -1.9313, last reward: -0.0207, gradient norm: 0.6286: 99%|#########9| 620/625 [01:26<00:00, 7.11it/s]
reward: -2.4325, last reward: -0.0171, gradient norm: 0.7832: 99%|#########9| 620/625 [01:27<00:00, 7.11it/s]
reward: -2.4325, last reward: -0.0171, gradient norm: 0.7832: 99%|#########9| 621/625 [01:27<00:00, 7.13it/s]
reward: -2.1134, last reward: -0.0144, gradient norm: 1.96: 99%|#########9| 621/625 [01:27<00:00, 7.13it/s]
reward: -2.1134, last reward: -0.0144, gradient norm: 1.96: 100%|#########9| 622/625 [01:27<00:00, 7.10it/s]
reward: -2.4572, last reward: -0.0500, gradient norm: 0.5838: 100%|#########9| 622/625 [01:27<00:00, 7.10it/s]
reward: -2.4572, last reward: -0.0500, gradient norm: 0.5838: 100%|#########9| 623/625 [01:27<00:00, 7.08it/s]
reward: -2.3818, last reward: -0.0019, gradient norm: 0.8623: 100%|#########9| 623/625 [01:27<00:00, 7.08it/s]
reward: -2.3818, last reward: -0.0019, gradient norm: 0.8623: 100%|#########9| 624/625 [01:27<00:00, 7.07it/s]
reward: -2.1253, last reward: -0.0001, gradient norm: 0.6622: 100%|#########9| 624/625 [01:27<00:00, 7.07it/s]
reward: -2.1253, last reward: -0.0001, gradient norm: 0.6622: 100%|##########| 625/625 [01:27<00:00, 7.06it/s]
reward: -2.1253, last reward: -0.0001, gradient norm: 0.6622: 100%|##########| 625/625 [01:27<00:00, 7.13it/s]
结论¶
在本教程中，我们学会了如何从零开始编写一个无状态环境。我们涉及了以下主题：
编码一个环境时需要关注的四个核心组件（
step,reset, 种子和构建规范）。 我们看到了这些方法和类与TensorDict类之间的交互；如何测试环境是否正确编码使用
check_env_specs();在无状态环境中如何追加变换以及如何编写自定义变换；
在完全可微分模拟器上训练策略的方法。
脚本总运行时间： (1分钟 27.902秒)