ActionMask

class torchrl.envs.transforms.ActionMask(action_key: NestedKey = 'action', mask_key: NestedKey = 'action_mask')

一个自适应动作掩码器。

此转换有助于通过掩码动作规范来确保随机生成的动作符合合法动作。它在执行步骤后从tensordict中读取掩码，并调整有限动作规范的掩码。

注意

未使用环境时，此转换将失败。

参数:

• action_key (NestedKey, optional) – 可以找到动作张量的键。默认为 "action"。

• mask_key (NestedKey, optional) – 可以找到动作掩码的键。默认为 "action_mask"。

示例

>>> import torch
>>> from torchrl.data.tensor_specs import Categorical, Binary, Unbounded, Composite
>>> from torchrl.envs.transforms import ActionMask, TransformedEnv
>>> from torchrl.envs.common import EnvBase
>>> class MaskedEnv(EnvBase):
...     def __init__(self, *args, **kwargs):
...         super().__init__(*args, **kwargs)
...         self.action_spec = Categorical(4)
...         self.state_spec = Composite(action_mask=Binary(4, dtype=torch.bool))
...         self.observation_spec = Composite(obs=Unbounded(3))
...         self.reward_spec = Unbounded(1)
...
...     def _reset(self, tensordict=None):
...         td = self.observation_spec.rand()
...         td.update(torch.ones_like(self.state_spec.rand()))
...         return td
...
...     def _step(self, data):
...         td = self.observation_spec.rand()
...         mask = data.get("action_mask")
...         action = data.get("action")
...         mask = mask.scatter(-1, action.unsqueeze(-1), 0)
...
...         td.set("action_mask", mask)
...         td.set("reward", self.reward_spec.rand())
...         td.set("done", ~mask.any().view(1))
...         return td
...
...     def _set_seed(self, seed) -> None:
...         pass
...
>>> torch.manual_seed(0)
>>> base_env = MaskedEnv()
>>> env = TransformedEnv(base_env, ActionMask())
>>> r = env.rollout(10)
>>> r["action_mask"]
tensor([[ True,  True,  True,  True],
        [ True,  True, False,  True],
        [ True,  True, False, False],
        [ True, False, False, False]])

forward(tensordict: TensorDictBase) → TensorDictBase

读取输入 tensordict，并对选定的键应用转换。

默认情况下，此方法

• 直接调用 _apply_transform()。

• 不调用 _step() 或 _call()。

此方法不会在 env.step 的任何点被调用。但是，它会在 sample() 中被调用。

注意

forward 也使用 dispatch 使用常规关键字参数来将参数名称转换为键。

示例

>>> class TransformThatMeasuresBytes(Transform):
...     '''Measures the number of bytes in the tensordict, and writes it under `"bytes"`.'''
...     def __init__(self):
...         super().__init__(in_keys=[], out_keys=["bytes"])
...
...     def forward(self, tensordict: TensorDictBase) -> TensorDictBase:
...         bytes_in_td = tensordict.bytes()
...         tensordict["bytes"] = bytes
...         return tensordict
>>> t = TransformThatMeasuresBytes()
>>> env = env.append_transform(t) # works within envs
>>> t(TensorDict(a=0))  # Works offline too.