go

agent.py

@@ -117,7 +117,7 @@ class qLearningAgent:
             v = tr.get(ind,np.zeros(len(Action)))
             v[self._action_index] += 1 
             tr[ind] = v
-        print(self.trace[0])
+        # print(self.trace[0])
         # print(np.sum(self.trace,axis=1))
         pass