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:
  • action (np.ndarray) – The action taken by the agent.
  • agent_info (dict[str, np.ndarray]) – Extra agent information.
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.