rlightning.buffer.replay_buffer

Replay buffer implementation.

class rlightning.buffer.replay_buffer.ReplayBuffer(config: BufferConfig, obs_preprocessor: Preprocessor | None = <function default_obs_preprocessor>, reward_preprocessor: Preprocessor | None = <function default_reward_preprocessor>, env_ret_preprocess_fn: Callable | None = <function default_env_ret_preprocess_fn>, policy_resp_preprocess_fn: Callable | None = <function default_policy_resp_preprocess_fn>, preprocess_fn: Callable | None = <function default_preprocess_fn>, postprocess_fn: Callable | None = <function default_postprocess_fn>)[source]

Bases: DataBuffer

Replay buffer usually for off-policy algorithms.

sample(batch_size: int | None = None, shuffle: bool | None = True, drop_last: bool | None = True) List[Dict][source]

Sample a batch of data from the buffer.