InitTracker¶
- class torchrl.envs.transforms.InitTracker(init_key: str = 'is_init')[source]¶
Reset tracker.
This transform populates the step/reset tensordict with a reset tracker entry that is set to
True
wheneverreset()
is called.- Parameters:
init_key (NestedKey, optional) – the key to be used for the tracker entry. In case of multiple _reset flags, this key is used as the leaf replacement for each.
Examples
>>> from torchrl.envs.libs.gym import GymEnv >>> env = TransformedEnv(GymEnv("Pendulum-v1"), InitTracker()) >>> td = env.reset() >>> print(td["is_init"]) tensor(True) >>> td = env.rand_step(td) >>> print(td["next", "is_init"]) tensor(False)
- forward(tensordict: TensorDictBase) TensorDictBase [source]¶
Reads the input tensordict, and for the selected keys, applies the transform.
- transform_observation_spec(observation_spec: TensorSpec) TensorSpec [source]¶
Transforms the observation spec such that the resulting spec matches transform mapping.
- Parameters:
observation_spec (TensorSpec) – spec before the transform
- Returns:
expected spec after the transform