garage.sampler._dtypes
¶
Datatypes used by multiple Samplers or Workers.
-
class
InProgressEpisode
(env, initial_observation=None)¶ An in-progress episode.
Compared to EpisodeBatch, this datatype does less checking, only contains one episodes, and uses lists instead of numpy arrays to make stepping faster.
Parameters: - env (Environment) – The environment the trajectory is being collected in.
- initial_observation (np.ndarray) – The first observation. If None, the environment will be reset to generate this observation.
-
last_obs
¶ The last observation in the epside.
Type: np.ndarray
-
step
(self, action, agent_info)¶ Step the episode using an action from an agent.
Parameters: Returns: The new observation from the environment.
Return type: np.ndarray
-
to_batch
(self)¶ Convert this in-progress episode into a EpisodeBatch.
Returns: This episode as a batch. Return type: EpisodeBatch Raises: AssertionError
– If this episode contains no time steps.