BaseWorker¶
-
class
maze.train.parallelization.base_worker.BaseWorker¶ This class holds a policy as well an env in order to step through the env, by producing action from the policy and recoding the rollout to be processed by the learner.
-
abstract
rollout() → Union[Tuple[maze.train.parallelization.base_worker.BaseWorkerOutput, List], Tuple[numpy.ndarray, List]]¶ Interface to performs an agent rollout, that is sample actions, step through the env for a maximum of n_rollout_steps and collect data.
- Returns
This rollout as an ActorOutput or array of ActorOutputs
-
abstract