d3rlpy.dataset.create_infinite_replay_buffer

d3rlpy.dataset.create_infinite_replay_buffer(episodes=None, transition_picker=None, trajectory_slicer=None, writer_preprocessor=None, env=None)[source]

Builds infinite replay buffer.

This function is a shortcut alias to build replay buffer with InfiniteBuffer.

Parameters

  • episodes (Optional[Sequence[d3rlpy.dataset.components.EpisodeBase]]) – List of episodes to initialize replay buffer.

  • transition_picker (Optional[d3rlpy.dataset.transition_pickers.TransitionPickerProtocol]) – Transition picker implementation for Q-learning-based algorithms. If None is given, BasicTransitionPicker is used by default.

  • trajectory_slicer (Optional[d3rlpy.dataset.trajectory_slicers.TrajectorySlicerProtocol]) – Trajectory slicer implementation for Transformer-based algorithms. If None is given, BasicTrajectorySlicer is used by default.

  • writer_preprocessor (Optional[d3rlpy.dataset.writers.WriterPreprocessProtocol]) – Writer preprocessor implementation. If None is given, BasicWriterPreprocess is used by default.

  • env (Optional[Union[gym.core.Env[Any, Any], gymnasium.core.Env[Any, Any]]]) – Gym environment to extract shapes of observations and action.

Returns

Replay buffer.

Return type

d3rlpy.dataset.replay_buffer.ReplayBuffer