OakEmuEnvFactory
python
OakEmuEnvFactory(game_configuration: str | PathLike | GameConfiguration, model_configuration: str | PathLike | ModelConfiguration, training_configuration: str | PathLike | TrainingConfiguration | None, observation_shape_order: Literal['hwf', 'fhw'], training_mode: TrainingMode = TrainingMode.TRAINING, dump_directory: str | PathLike | None = None) -> NoneFactory for creating OakEmu environment instances.
Initialize the OakEmuEnvFactory.
Parameters:
game_configuration(str | PathLike | GameConfiguration) – Path to or instance of GameConfiguration.model_configuration(str | PathLike | ModelConfiguration) – Path to or instance of ModelConfiguration.observation_shape_order(Literal['hwf', 'fhw']) – Dimension order for observations.training_mode(TrainingMode) – The training mode to use.dump_directory(str | PathLike | None) – Optional directory for environment dumps.
Properties
action_shape
python
action_shape: intGet the action shape.
Returns:
int– The number of discrete actions.
action_space
python
action_space: DiscreteGet the action space.
Returns:
Discrete– The Discrete action space.
game_configuration
python
game_configuration: GameConfigurationGet the game configuration.
Returns:
GameConfiguration– The GameConfiguration instance.
model_configuration
python
model_configuration: ModelConfigurationGet the model configuration.
Returns:
ModelConfiguration– The ModelConfiguration instance.
name
python
name: strGet the name of the game.
Returns:
str– The game name.
observation_shape
python
observation_shape: tuple[int, int, int]Get the observation shape.
Returns:
tuple[int, int, int]– The observation shape.
observation_space
python
observation_space: BoxGet the observation space.
Returns:
Box– The Box observation space.
training_mode
python
training_mode: TrainingModeGet the training mode.
Returns:
TrainingMode– The training mode.
Methods
create
python
create() -> OakEmuEnvCreate a new OakEmuEnv instance with the specified mode.
Returns:
OakEmuEnv– A new OakEmuEnv instance.