ray.rllib.utils.replay_buffers.multi_agent_prioritized_replay_buffer.MultiAgentPrioritizedReplayBuffer#

class ray.rllib.utils.replay_buffers.multi_agent_prioritized_replay_buffer.MultiAgentPrioritizedReplayBuffer(capacity: int = 10000, storage_unit: str = 'timesteps', num_shards: int = 1, replay_mode: str = 'independent', replay_sequence_override: bool = True, replay_sequence_length: int = 1, replay_burn_in: int = 0, replay_zero_init_states: bool = True, underlying_buffer_config: dict = None, prioritized_replay_alpha: float = 0.6, prioritized_replay_beta: float = 0.4, prioritized_replay_eps: float = 1e-06, **kwargs)[source]#

Bases: MultiAgentReplayBuffer, PrioritizedReplayBuffer

A prioritized replay buffer shard for multiagent setups.

This buffer is meant to be run in parallel to distribute experiences across num_shards shards. Unlike simpler buffers, it holds a set of buffers - one for each policy ID.

DeveloperAPI: This API may change across minor Ray releases.

Methods

`__init__`	Initializes a MultiAgentReplayBuffer instance.
`add`	Adds a batch to the appropriate policy's replay 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.
`replay`	DeveloperAPI: This API may change across minor Ray releases.
`sample`	Samples a MultiAgentBatch of `num_items` per one policy's buffer.
`set_state`	Restores all local state to the provided `state`.
`stats`	Returns the stats of this buffer and all underlying buffers.
`update_priorities`	Updates the priorities of underlying replay buffers.