ExcludeTransform

class torchrl.envs.transforms.ExcludeTransform(*excluded_keys, inverse: bool = False)

排除数据中的键。

参数:

• *excluded_keys (iterable of NestedKey) – 要排除的键的名称。如果键不存在，则简单地忽略它。

• inverse (bool, optional) – 如果为 True，则排除将在 inv 调用期间发生。默认为 False。

示例

>>> import gymnasium
>>> from torchrl.envs import GymWrapper
>>> env = TransformedEnv(
...     GymWrapper(gymnasium.make("Pendulum-v1")),
...     ExcludeTransform("truncated")
... )
>>> env.rollout(3)
TensorDict(
    fields={
        action: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.float32, is_shared=False),
        done: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
        next: TensorDict(
            fields={
                done: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.bool, is_shared=False),
                observation: Tensor(shape=torch.Size([3, 3]), device=cpu, dtype=torch.float32, is_shared=False),
                reward: Tensor(shape=torch.Size([3, 1]), device=cpu, dtype=torch.float32, is_shared=False)},
            batch_size=torch.Size([3]),
            device=cpu,
            is_shared=False),
        observation: Tensor(shape=torch.Size([3, 3]), device=cpu, dtype=torch.float32, is_shared=False)},
    batch_size=torch.Size([3]),
    device=cpu,
    is_shared=False)

forward(next_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()。

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

注意

forward 也可以使用 dispatch 将参数名称映射到键，来处理常规的关键字参数。

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.

transform_output_spec(output_spec: Composite) → Composite

转换输出规范，使结果规范与转换映射匹配。

此方法通常应保持不变。更改应通过 transform_observation_spec()、transform_reward_spec() 和 transform_full_done_spec() 实现。 :param output_spec: 转换前的 spec :type output_spec: TensorSpec

返回:

转换后的预期规范