ray.rllib.policy.eager_tf_policy_v2.EagerTFPolicyV2.stats_fn#

EagerTFPolicyV2.stats_fn(train_batch: SampleBatch) Dict[str, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor][source]#

Stats function. Returns a dict of statistics.

Parameters:

train_batch – The SampleBatch (already) used for training.

Returns:

The stats dict.