ray.rllib.utils.replay_buffers.reservoir_replay_buffer.ReservoirReplayBuffer#

class ray.rllib.utils.replay_buffers.reservoir_replay_buffer.ReservoirReplayBuffer(capacity: int = 10000, storage_unit: str = 'timesteps', **kwargs)[source]#

Bases: ReplayBuffer

This buffer implements reservoir sampling.

The algorithm has been described by Jeffrey S. Vitter in “Random sampling with a reservoir”.

Methods

`__init__`	Initializes a ReservoirBuffer 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`	Samples `num_items` items from this buffer.
`set_state`	Restores all local state to the provided `state`.
`stats`	Returns the stats of this buffer.