evorl.algorithms.contrib.a2c_v2

Module Contents

Classes

A2CWorkflow

Functions

get_train_episode_return

Handle episode return array with MISSING_REWARD, i.e., returned from multiple call of average_episode_discount_return.

API

class evorl.algorithms.contrib.a2c_v2.A2CWorkflow(env: evorl.envs.Env, agent: evorl.agent.Agent, optimizer: optax.GradientTransformation, evaluator: evorl.evaluators.Evaluator, config: omegaconf.DictConfig)[source]

Bases: evorl.algorithms.a2c.A2CWorkflow

learn(state: evorl.types.State) → evorl.types.State[source]
classmethod name()[source]
evorl.algorithms.contrib.a2c_v2.get_train_episode_return(episode_return_arr: collections.abc.Sequence[float], reduce_fn=_default_episode_return_reduce_fn)[source]

Handle episode return array with MISSING_REWARD, i.e., returned from multiple call of average_episode_discount_return.