ray.rllib.utils.replay_buffers.replay_buffer.ReplayBuffer.sample#

ReplayBuffer.sample(num_items: int | None = None, **kwargs) SampleBatch | MultiAgentBatch | Dict[str, Any] | None[source]#

Samples num_items items from this buffer.

The items depend on the buffer’s storage_unit. Samples in the results may be repeated.

Examples for sampling results:

1) If storage unit ‘timesteps’ has been chosen and batches of size 5 have been added, sample(5) will yield a concatenated batch of 15 timesteps.

2) If storage unit ‘sequences’ has been chosen and sequences of different lengths have been added, sample(5) will yield a concatenated batch with a number of timesteps equal to the sum of timesteps in the 5 sampled sequences.

3) If storage unit ‘episodes’ has been chosen and episodes of different lengths have been added, sample(5) will yield a concatenated batch with a number of timesteps equal to the sum of timesteps in the 5 sampled episodes.

Parameters:
  • num_items – Number of items to sample from this buffer.

  • **kwargs – Forward compatibility kwargs.

Returns:

Concatenated batch of items.