CustomModelComposer

class maze.perception.models.custom_model_composer.CustomModelComposer(action_spaces_dict: Dict[str | int, gymnasium.spaces.Dict], observation_spaces_dict: Dict[str | int, gymnasium.spaces.Dict], agent_counts_dict: Dict[str | int, int], distribution_mapper_config: None | Mapping[str, Any] | Any, policy: None | Mapping[str, Any] | Any, critic: None | Mapping[str, Any] | Any)

Composes models from explicit model definitions.

Parameters:

• action_spaces_dict – Dict of sub-step id to action space.

• observation_spaces_dict – Dict of sub-step id to observation space.

• distribution_mapper_config – Distribution mapper configuration.

• policy – Mapping of sub-step keys to models.

• critic – Configuration for the critic composer.

classmethod check_model_config(model_config: None | Mapping[str, Any] | Any) → None

Asserts the provided model config for consistency. :param model_config: The model config to check.

property critic: TorchStateCritic | TorchStateActionCritic | None

(overrides BaseModelComposer)

Return the critic networks.

property policy: TorchPolicy | None

(overrides BaseModelComposer)

Return the policy networks.