`evorl.evaluators.episode_collector`¶

Module Contents¶

Classes¶

EpisodeCollector

Evaluate and return eval metrics and episodic trajectory.

API¶

class evorl.evaluators.episode_collector.EpisodeCollector[source]¶

Bases: evorl.types.PyTreeNode

Evaluate and return eval metrics and episodic trajectory.

EpisodeCollector is similar as Evaluator, but it also returns the trajectories. When evaluating the agent, call rollout().

Variables:

env – Vectorized environment w/o autoreset.
action_fn – The agent action function.
max_episode_steps – The maximum number of steps in an episode.
env_extra_fields – The extra fields to collect from the environment.
discount – The discount factor.

action_fn: evorl.agent.AgentActionFn¶: None

discount: float¶: 1.0

env: evorl.envs.Env¶: None

env_extra_fields: collections.abc.Sequence[str]¶: ()

max_episode_steps: int¶: ‘pytree_field(…)’

rollout(agent_state, key: chex.PRNGKey, num_episodes: int) → tuple[evorl.metrics.EvaluateMetric, evorl.sample_batch.SampleBatch][source]¶

rollout_fn: evorl.rollout.RolloutFn¶: ‘pytree_field(…)’