ray.rllib.policy.policy.Policy.restore_connectors#

Policy.restore_connectors(state: Dict[str, numpy.array | jnp.ndarray | tf.Tensor | torch.Tensor | dict | tuple])[source]#

Restore agent and action connectors if configs available.

Parameters:

state – The new state to set this policy to. Can be obtained by calling self.get_state().

PublicAPI (alpha): This API is in alpha and may change before becoming stable.