ray.rllib.core.rl_module.rl_module.RLModule._forward_inference

RLModule._forward_inference(batch: Dict[str, Any], **kwargs) → Dict[str, Any]

Forward-pass used for action computation without exploration behavior.

Override this method only, if you need specific behavior for non-exploratory action computation behavior. If you have only one generic behavior for all phases of training and evaluation, override self._forward() instead.

By default, this calls the generic self._forward() method.