update

tutorial-contents/405_DQN_Reinforcement_learning.py

@@ -74,6 +74,7 @@ class DQN(object):
         # target parameter update
         if self.learn_step_counter % TARGET_REPLACE_ITER == 0:
             self.target_net.load_state_dict(self.eval_net.state_dict())
+        self.learn_step_counter += 1
 
         # sample batch transitions
         sample_index = np.random.choice(MEMORY_CAPACITY, BATCH_SIZE)