class maze.train.parallelization.broadcasting_container.BroadcastingContainer

Synchronizes policy updates and other information across workers on local machine.

Used for dummy and sub-process distribution scenarios.

The BroadcastingContainer object can be read by all workers in order to update their policy, and it can be accessed by the main thread to write the updated policy from the learner into it.

aux_data() → Optional[Dict]

Return auxiliary data stored together with the policy.

policy_state_dict() → Dict

Return the current policy state dict.


Return the current policy version number (to check whether fetching a new state dict is necessary).

set_policy_state_dict(state_dict: Dict, aux_data: Dict = None) → NoReturn

Store new policy version.

  • state_dict – New state dict to store

  • aux_data – Dictionary with any auxiliary data to share

set_stop_flag() → NoReturn

Signal to the workers to exit after they finish the current rollout.


True if workers should exit.