目录
目录

注意

转到末尾 以下载完整示例代码。

多任务环境中的任务特定策略

本教程详细介绍了如何使用多任务策略和批量环境。

本教程结束时，您将能够编写策略，利用一组独立的权重，在多种场景下计算动作。 您还将能够并行执行多种环境。

from tensordict.nn import TensorDictModule, TensorDictSequential
from torch import nn

from torchrl.envs import CatTensors, Compose, DoubleToFloat, ParallelEnv, TransformedEnv
from torchrl.envs.libs.dm_control import DMControlEnv
from torchrl.modules import MLP

我们设计了两个环境：一个是需要完成站立任务的人形机器人环境，另一个是需要学习行走的环境。

env1 = DMControlEnv("humanoid", "stand")
env1_obs_keys = list(env1.observation_spec.keys())
env1 = TransformedEnv(
    env1,
    Compose(
        CatTensors(env1_obs_keys, "observation_stand", del_keys=False),
        CatTensors(env1_obs_keys, "observation"),
        DoubleToFloat(
            in_keys=["observation_stand", "observation"],
            in_keys_inv=["action"],
        ),
    ),
)
env2 = DMControlEnv("humanoid", "walk")
env2_obs_keys = list(env2.observation_spec.keys())
env2 = TransformedEnv(
    env2,
    Compose(
        CatTensors(env2_obs_keys, "observation_walk", del_keys=False),
        CatTensors(env2_obs_keys, "observation"),
        DoubleToFloat(
            in_keys=["observation_walk", "observation"],
            in_keys_inv=["action"],
        ),
    ),
)

tdreset1 = env1.reset()
tdreset2 = env2.reset()

# With LazyStackedTensorDict, stacking is done in a lazy manner: the original tensordicts
# can still be recovered by indexing the main tensordict
tdreset = LazyStackedTensorDict.lazy_stack([tdreset1, tdreset2], 0)
assert tdreset[0] is tdreset1

print(tdreset[0])

TensorDict(
    fields={
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)

政策

我们将设计一种策略，其中主干网络读取“observation”键。 随后，特定的子组件将准备堆叠的张量字典（tensordicts）中的“observation_stand”和 “observation_walk”键（如果存在），并将其传入专用的子网络。

action_dim = env1.action_spec.shape[-1]

policy_common = TensorDictModule(
    nn.Linear(67, 64), in_keys=["observation"], out_keys=["hidden"]
)
policy_stand = TensorDictModule(
    MLP(67 + 64, action_dim, depth=2),
    in_keys=["observation_stand", "hidden"],
    out_keys=["action"],
)
policy_walk = TensorDictModule(
    MLP(67 + 64, action_dim, depth=2),
    in_keys=["observation_walk", "hidden"],
    out_keys=["action"],
)
seq = TensorDictSequential(
    policy_common, policy_stand, policy_walk, partial_tolerant=True
)

让我们检查一下我们的序列是否为单个环境（站立）输出动作。

seq(env1.reset())

TensorDict(
    fields={
        action: Tensor(shape=torch.Size([21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)

让我们检查一下我们的序列是否为单个环境（行走）输出动作。

seq(env2.reset())

TensorDict(
    fields={
        action: Tensor(shape=torch.Size([21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)

这也可以与堆栈一起工作：现在站立和行走键已经消失，因为它们不是所有张量字典共有的。但是TensorDictSequential仍然执行了操作。请注意，主干是以向量化的方式执行的——而不是通过循环——这更高效。

seq(tdreset)

LazyStackedTensorDict(
    fields={
        action: Tensor(shape=torch.Size([2, 21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.float32, is_shared=False),
        observation: Tensor(shape=torch.Size([2, 67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    exclusive_fields={
        0 ->
            observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        1 ->
            observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False)},
    batch_size=torch.Size([2]),
    device=None,
    is_shared=False,
    stack_dim=0)

并行执行多种任务

如果公共的键值对具有相同的规格（特别是其形状和数据类型必须一致），则可以对这些操作进行并行化处理（例如，若不同观测值的形状不同，但均通过同一键进行索引，则无法执行以下操作）。

如果 ParallelEnv 接收到一个单一的环境创建函数，它将假定需要执行单个任务；如果提供的是函数列表，则它将假定我们处于多任务设置中。

def env1_maker():
    return TransformedEnv(
        DMControlEnv("humanoid", "stand"),
        Compose(
            CatTensors(env1_obs_keys, "observation_stand", del_keys=False),
            CatTensors(env1_obs_keys, "observation"),
            DoubleToFloat(
                in_keys=["observation_stand", "observation"],
                in_keys_inv=["action"],
            ),
        ),
    )


def env2_maker():
    return TransformedEnv(
        DMControlEnv("humanoid", "walk"),
        Compose(
            CatTensors(env2_obs_keys, "observation_walk", del_keys=False),
            CatTensors(env2_obs_keys, "observation"),
            DoubleToFloat(
                in_keys=["observation_walk", "observation"],
                in_keys_inv=["action"],
            ),
        ),
    )


env = ParallelEnv(2, [env1_maker, env2_maker])
assert not env._single_task

tdreset = env.reset()
print(tdreset)
print(tdreset[0])
print(tdreset[1])  # should be different

LazyStackedTensorDict(
    fields={
        done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        observation: Tensor(shape=torch.Size([2, 67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    exclusive_fields={
        0 ->
            observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        1 ->
            observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False)},
    batch_size=torch.Size([2]),
    device=None,
    is_shared=False,
    stack_dim=0)
TensorDict(
    fields={
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)
TensorDict(
    fields={
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)

让我们将输出通过我们的网络。

tdreset = seq(tdreset)
print(tdreset)
print(tdreset[0])
print(tdreset[1])  # should be different but all have an "action" key


env.step(tdreset)  # computes actions and execute steps in parallel
print(tdreset)
print(tdreset[0])
print(tdreset[1])  # next_observation has now been written

LazyStackedTensorDict(
    fields={
        action: Tensor(shape=torch.Size([2, 21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.float32, is_shared=False),
        observation: Tensor(shape=torch.Size([2, 67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    exclusive_fields={
        0 ->
            observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        1 ->
            observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False)},
    batch_size=torch.Size([2]),
    device=None,
    is_shared=False,
    stack_dim=0)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)
LazyStackedTensorDict(
    fields={
        action: Tensor(shape=torch.Size([2, 21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.float32, is_shared=False),
        next: LazyStackedTensorDict(
            fields={
                done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                observation: Tensor(shape=torch.Size([2, 67]), device=cpu, dtype=torch.float32, is_shared=False),
                reward: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.float64, is_shared=False),
                terminated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            exclusive_fields={
                0 ->
                    observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
                1 ->
                    observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False)},
            batch_size=torch.Size([2]),
            device=None,
            is_shared=False,
            stack_dim=0),
        observation: Tensor(shape=torch.Size([2, 67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    exclusive_fields={
        0 ->
            observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        1 ->
            observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False)},
    batch_size=torch.Size([2]),
    device=None,
    is_shared=False,
    stack_dim=0)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, 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([67]), device=cpu, dtype=torch.float32, is_shared=False),
                observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
                reward: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float64, is_shared=False),
                terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([]),
            device=None,
            is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([64]), device=cpu, dtype=torch.float32, 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([67]), device=cpu, dtype=torch.float32, is_shared=False),
                observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
                reward: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.float64, is_shared=False),
                terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
            batch_size=torch.Size([]),
            device=None,
            is_shared=False),
        observation: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([1]), device=cpu, dtype=torch.bool, is_shared=False)},
    batch_size=torch.Size([]),
    device=None,
    is_shared=False)

展开

td_rollout = env.rollout(100, policy=seq, return_contiguous=False)

td_rollout[:, 0]  # tensordict of the first step: only the common keys are shown

LazyStackedTensorDict(
    fields={
        action: Tensor(shape=torch.Size([2, 21]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        hidden: Tensor(shape=torch.Size([2, 64]), device=cpu, dtype=torch.float32, is_shared=False),
        next: LazyStackedTensorDict(
            fields={
                done: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                observation: Tensor(shape=torch.Size([2, 67]), device=cpu, dtype=torch.float32, is_shared=False),
                reward: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.float64, is_shared=False),
                terminated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                truncated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
            exclusive_fields={
                0 ->
                    observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
                1 ->
                    observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False)},
            batch_size=torch.Size([2]),
            device=None,
            is_shared=False,
            stack_dim=0),
        observation: Tensor(shape=torch.Size([2, 67]), device=cpu, dtype=torch.float32, is_shared=False),
        terminated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        truncated: Tensor(shape=torch.Size([2, 1]), device=cpu, dtype=torch.bool, is_shared=False)},
    exclusive_fields={
        0 ->
            observation_stand: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False),
        1 ->
            observation_walk: Tensor(shape=torch.Size([67]), device=cpu, dtype=torch.float32, is_shared=False)},
    batch_size=torch.Size([2]),
    device=None,
    is_shared=False,
    stack_dim=0)

td_rollout[0]  # tensordict of the first env: the stand obs is present

env.close()
del env

脚本总运行时间： (0 分钟 51.107 秒)

估计内存使用量： 322 MB

通过 Sphinx-Gallery 生成的画廊

文档

访问 PyTorch 的全面开发人员文档

查看文档

教程

获取面向初学者和高级开发人员的深入教程

查看教程

资源

查找开发资源并解答您的问题

查看资源