tf_agents.environments.suite_gym.load

Loads the selected environment and wraps it with the specified wrappers.

tf_agents.environments.suite_gym.load(
    environment_name: Text,
    discount: tf_agents.typing.types.Float = 1.0,
    max_episode_steps: Optional[types.Int] = None,
    gym_env_wrappers: Sequence[tf_agents.typing.types.GymEnvWrapper] = (),
    env_wrappers: Sequence[tf_agents.typing.types.PyEnvWrapper] = (),
    spec_dtype_map: Optional[Dict[gym.Space, np.dtype]] = None,
    gym_kwargs: Optional[Dict[str, Any]] = None,
    render_kwargs: Optional[Dict[str, Any]] = None
) -> tf_agents.environments.PyEnvironment

Used in the notebooks

Used in the tutorials

Note that by default a TimeLimit wrapper is used to limit episode lengths to the default benchmarks defined by the registered environments.

environment_name Name for the environment to load.
discount Discount to use for the environment.
max_episode_steps If None the max_episode_steps will be set to the default step limit defined in the environment's spec. No limit is applied if set to 0 or if there is no max_episode_steps set in the environment's spec.
gym_env_wrappers Iterable with references to wrapper classes to use directly on the gym environment.
env_wrappers Iterable with references to wrapper classes to use on the gym_wrapped environment.
spec_dtype_map A dict that maps gym spaces to np dtypes to use as the default dtype for the arrays. An easy way how to configure a custom mapping through Gin is to define a gin-configurable function that returns desired mapping and call it in your Gin congif file, for example: suite_gym.load.spec_dtype_map = @get_custom_mapping().
gym_kwargs Optional kwargs to pass to the Gym environment class.
render_kwargs Optional kwargs for rendering to pass to render() of the gym_wrapped environment.

A PyEnvironment instance.