ray.rllib.evaluation.rollout_worker.RolloutWorker.set_is_policy_to_train
ray.rllib.evaluation.rollout_worker.RolloutWorker.set_is_policy_to_train#
- RolloutWorker.set_is_policy_to_train(is_policy_to_train: Union[Container[str], Callable[[str, Optional[Union[SampleBatch, MultiAgentBatch]]], bool]]) None [source]#
Sets
self.is_policy_to_train()
to a new callable.- Parameters
is_policy_to_train – A container of policy IDs to be trained or a callable taking PolicyID and - optionally - SampleBatchType and returning a bool (trainable or not?). If None, will keep the existing setup in place. Policies, whose IDs are not in the list (or for which the callable returns False) will not be updated.