예제 #1
0
 def extra_compute_action_fetches(self):
     return dict(TFPolicy.extra_compute_action_fetches(self),
                 **self._extra_action_fetches)
예제 #2
0
 def extra_compute_action_fetches(self):
     return dict(TFPolicy.extra_compute_action_fetches(self),
                 **{BEHAVIOUR_LOGITS: self.model.outputs})
예제 #3
0
파일: dqn_policy.py 프로젝트: zzz622848/ray 
 def extra_compute_action_fetches(self):
     return dict(
         TFPolicy.extra_compute_action_fetches(self), **{
             "q_values": self.q_values,
         })
예제 #4
0
 def extra_compute_action_fetches(self):
     return dict(TFPolicy.extra_compute_action_fetches(self),
                 **{SampleBatch.VF_PREDS: self.vf})