多任务环境中特定于任务的策略¶

本教程详细介绍了如何使用多任务策略和批处理环境。

在本教程结束时，您将能够编写策略可以使用一组不同的权重计算不同设置中的操作。您还可以并行执行不同的环境。

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，一个必须完成站立任务的人形生物另一个必须学会走路。

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¶

我们将设计一个策略，让主干读取 “observation” 键。然后特定的子组件将准备好 “observation_stand” 和堆叠 Tensordict 的 “observation_walk” 键（如果存在），并通过专用子网络传递它们。

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输出了单个 env （stand）的 action。

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输出了单个环境（walk）的动作。

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)

这也适用于堆栈：现在 stand 和 walk 键具有消失了，因为它们并非由所有 Tensordict 共享。但仍然执行了手术。请注意， backbone 以矢量化的方式执行 - 而不是在循环中 - 这样效率更高。TensorDictSequential

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)

并行执行各种任务¶

如果公共键值对共享相同的规范（特别是它们的 shape 和 dtype 必须匹配）：你不能执行如果观察形状不同，但由相同的密钥）。

如果 ParallelEnv 收到单个 env making 函数，它将假定必须执行单个任务。如果提供了函数列表，则它将假设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)

让我们通过我们的网络传递输出。

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)

推出¶

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 51.107 秒）

估计内存使用量：322 MB

由 Sphinx-Gallery 生成的图库

多任务环境中特定于任务的策略¶

政策¶

并行执行各种任务¶

推出¶

文档

教程

资源