ray.rllib.policy.eager_tf_policy_v2.EagerTFPolicyV2.grad_stats_fn

EagerTFPolicyV2.grad_stats_fn(train_batch: SampleBatch, grads: List[Tuple[numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor]] | List[numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor]) → Dict[str, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor]

Gradient stats function. Returns a dict of statistics.

Parameters:

train_batch – The SampleBatch (already) used for training.

Returns:

The stats dict.