ImpalaRunner¶
-
class
maze.train.trainers.impala.impala_runners.
ImpalaRunner
(state_dict_dump_file: str, dump_interval: Optional[int], spaces_config_dump_file: str, normalization_samples: int, eval_concurrency: int)¶ Common superclass for IMPALA runners, implementing the main training controls.
-
abstract
create_distributed_eval_env
(env_factory: Callable[], Union[maze.core.env.structured_env.StructuredEnv, maze.core.env.structured_env_spaces_mixin.StructuredEnvSpacesMixin]], eval_concurrency: int, logging_prefix: str) → maze.train.parallelization.vector_env.vector_env.VectorEnv¶ The individual runners implement the setup of the distributed eval env
-
abstract
create_distributed_rollout_actors
(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]], policy: maze.core.agent.torch_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]) → maze.train.parallelization.distributed_actors.distributed_actors.DistributedActors¶ The individual runners implement the setup of the distributed training rollout actors
-
setup
(cfg: omegaconf.DictConfig) → None¶ (overrides
TrainingRunner
)See
setup()
.
-
abstract