DummyDistributedWorkersWithBuffer¶
-
class
maze.train.parallelization.distributed_actors.dummy_distributed_workers_with_buffer.
DummyDistributedWorkersWithBuffer
(env_factory: Callable[], Union[maze.core.env.structured_env.StructuredEnv, maze.core.env.structured_env_spaces_mixin.StructuredEnvSpacesMixin, maze.core.log_stats.log_stats_env.LogStatsEnv]], worker_policy: maze.core.agent.torch_policy.TorchPolicy, n_rollout_steps: int, n_workers: int, batch_size: int, rollouts_per_iteration: int, split_rollouts_into_transitions: bool, env_instance_seeds: List[int], replay_buffer: maze.train.trainers.common.replay_buffer.replay_buffer.BaseReplayBuffer)¶ Dummy implementation of distributed workers with buffer creates the workers as a list. Once the outputs are to be collected, it simply rolls them out in a loop until is has enough to be added to the buffer.
-
broadcast_updated_policy
(state_dict: Dict) → None¶ (overrides
BaseDistributedWorkersWithBuffer
)Store the newest policy in the shared network object
-
collect_rollouts
() → Tuple[float, float, float]¶ (overrides
BaseDistributedWorkersWithBuffer
)- implementation of
BaseDistributedWorkersWithBuffer
interface
-
start
() → None¶ (overrides
BaseDistributedWorkersWithBuffer
)Nothing to do in dummy implementation
-
stop
() → None¶ (overrides
BaseDistributedWorkersWithBuffer
)Nothing to do in dummy implementation
-