A2C

class maze.train.trainers.a2c.a2c_trainer.A2C(algorithm_config: A2CAlgorithmConfig | PPOAlgorithmConfig | ImpalaAlgorithmConfig, rollout_generator: RolloutGenerator | DistributedActors, evaluator: RolloutEvaluator | None, model: TorchActorCritic, model_selection: BestModelSelection | None)

Advantage Actor Critic. Suitable for multi-step and multi-agent scenarios.