ray.rllib.policy.eager_tf_policy_v2.EagerTFPolicyV2.extra_action_out_fn

EagerTFPolicyV2.extra_action_out_fn() → Dict[str, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor]

Extra values to fetch and return from compute_actions().

Returns:

An extra fetch-dict to be passed to and

returned from the compute_actions() call.

Return type:

Dict[str, TensorType]