ray.rllib.policy.torch_policy_v2.TorchPolicyV2.stats_fn

TorchPolicyV2.stats_fn(train_batch: SampleBatch) → Dict[str, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor]

Stats function. Returns a dict of statistics.

Parameters:

train_batch – The SampleBatch (already) used for training.

Returns:

The stats dict.