d3rlpy.datasets.get_minari

d3rlpy.datasets.get_minari(env_name, transition_picker=None, trajectory_slicer=None, render_mode=None, tuple_observation=False)

Returns minari dataset and envrironment.

The dataset is provided through minari.

Parameters:

• env_name (str) – environment id of minari dataset.

• transition_picker (Optional[TransitionPickerProtocol]) – TransitionPickerProtocol object.

• trajectory_slicer (Optional[TrajectorySlicerProtocol]) – TrajectorySlicerProtocol object.

• render_mode (Optional[str]) – Mode of rendering (human, rgb_array).

• tuple_observation (bool) – Flag to include goals as tuple element.

Returns:

tuple of d3rlpy.dataset.ReplayBuffer and gym environment.

Return type:

Tuple[ReplayBuffer, Env[Any, Any]]