ray.rllib.policy.eager_tf_policy_v2.EagerTFPolicyV2.extra_action_out_fn#

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

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]