ImpalaDevRunner

class maze.train.trainers.impala.impala_runners.ImpalaDevRunner(state_dict_dump_file: str, dump_interval: int | None, spaces_config_dump_file: str, normalization_samples: int, eval_concurrency: int)

Runner for single-threaded training, based on SequentialVectorEnv.

create_distributed_eval_env(env_factory: Callable[[], MazeEnv | StructuredEnv], eval_concurrency: int, logging_prefix: str) → SequentialVectorEnv

create single-threaded env distribution

create_distributed_rollout_actors(env_factory: Callable[[], StructuredEnv | StructuredEnvSpacesMixin | LogStatsEnv], policy: TorchPolicy, n_rollout_steps: int, n_actors: int, batch_size: int, queue_out_of_sync_factor: float, env_instance_seeds: List[int], agent_instance_seeds: List[int]) → SequentialDistributedActors

Create dummy (sequentially-executed) actors.