ray.rllib.utils.policy.parse_policy_specs_from_checkpoint#
- ray.rllib.utils.policy.parse_policy_specs_from_checkpoint(path: str) Tuple[dict, Dict[str, PolicySpec], Dict[str, Dict[str, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor | dict | tuple]]][source]#
Read and parse policy specifications from a checkpoint file.
- Parameters:
path – Path to a policy checkpoint.
- Returns:
base policy config, dictionary of policy specs, and dictionary of policy states.
- Return type:
A tuple of
PublicAPI (alpha): This API is in alpha and may change before becoming stable.