ray.rllib.utils.replay_buffers.prioritized_replay_buffer.PrioritizedReplayBuffer#

class ray.rllib.utils.replay_buffers.prioritized_replay_buffer.PrioritizedReplayBuffer(capacity: int = 10000, storage_unit: str = 'timesteps', alpha: float = 1.0, **kwargs)[source]#

Bases: ReplayBuffer

This buffer implements Prioritized Experience Replay.

The algorithm has been described by Tom Schaul et. al. in “Prioritized Experience Replay”. See https://arxiv.org/pdf/1511.05952.pdf for the full paper.

DeveloperAPI: This API may change across minor Ray releases.

Methods

`__init__`	Initializes a PrioritizedReplayBuffer instance.
`add`	Adds a batch of experiences or other data to this buffer.
`apply`	Calls the given function with this Actor instance.
`get_host`	Returns the computer's network name.
`get_state`	Returns all local state.
`ping`	Ping the actor.
`sample`	Sample `num_items` items from this buffer, including prio.
`set_state`	Restores all local state to the provided `state`.
`stats`	Returns the stats of this buffer.
`update_priorities`	Update priorities of items at given indices.