ray.rllib.policy.eager_tf_policy_v2.EagerTFPolicyV2.extra_learn_fetches_fn#

EagerTFPolicyV2.extra_learn_fetches_fn() Dict[str, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor][source]#

Extra stats to be reported after gradient computation.

Returns:

An extra fetch-dict.

Return type:

Dict[str, TensorType]