ray.rllib.utils.replay_buffers.utils.sample_min_n_steps_from_buffer#

ray.rllib.utils.replay_buffers.utils.sample_min_n_steps_from_buffer(replay_buffer: ReplayBuffer, min_steps: int, count_by_agent_steps: bool) → SampleBatch | MultiAgentBatch | Dict[str, Any] | None[source]#

Samples a minimum of n timesteps from a given replay buffer.

This utility method is primarily used by the QMIX algorithm and helps with sampling a given number of time steps which has stored samples in units of sequences or complete episodes. Samples n batches from replay buffer until the total number of timesteps reaches train_batch_size.

Parameters:

  • replay_buffer – The replay buffer to sample from

  • num_timesteps – The number of timesteps to sample

  • count_by_agent_steps – Whether to count agent steps or env steps

Returns:

A concatenated SampleBatch or MultiAgentBatch with samples from the buffer.

DeveloperAPI: This API may change across minor Ray releases.