0f546db82bd5c161b1e8fb1aa46cebb28a2a3e80,contents/5_Deep_Q_Network/RL_brain.py,DeepQNetwork,learn,#DeepQNetwork#,140

Before Change


    def learn(self):
        // check to replace target parameters
        if self.learn_step_counter % self.replace_target_iter == 0:
            self._replace_target_params()
            print("\ntarget_params_replaced\n")

        // sample batch memory from all memory
        if self.memory_counter > self.memory_size:

After Change


    def learn(self):
        // check to replace target parameters
        if self.learn_step_counter % self.replace_target_iter == 0:
            self.sess.run(self.replace_target_op)
            print("\ntarget_params_replaced\n")

        // sample batch memory from all memory
        if self.memory_counter > self.memory_size:
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 6

Non-data size: 4

Instances


Project Name: MorvanZhou/Reinforcement-learning-with-tensorflow
Commit Name: 0f546db82bd5c161b1e8fb1aa46cebb28a2a3e80
Time: 2017-08-14
Author: morvanzhou@gmail.com
File Name: contents/5_Deep_Q_Network/RL_brain.py
Class Name: DeepQNetwork
Method Name: learn


Project Name: MorvanZhou/Reinforcement-learning-with-tensorflow
Commit Name: 0f546db82bd5c161b1e8fb1aa46cebb28a2a3e80
Time: 2017-08-14
Author: morvanzhou@gmail.com
File Name: contents/5.2_Prioritized_Replay_DQN/RL_brain.py
Class Name: DQNPrioritizedReplay
Method Name: learn


Project Name: MorvanZhou/Reinforcement-learning-with-tensorflow
Commit Name: 0f546db82bd5c161b1e8fb1aa46cebb28a2a3e80
Time: 2017-08-14
Author: morvanzhou@gmail.com
File Name: contents/6_OpenAI_gym/RL_brain.py
Class Name: DeepQNetwork
Method Name: learn


Project Name: MorvanZhou/Reinforcement-learning-with-tensorflow
Commit Name: 0f546db82bd5c161b1e8fb1aa46cebb28a2a3e80
Time: 2017-08-14
Author: morvanzhou@gmail.com
File Name: contents/5.3_Dueling_DQN/RL_brain.py
Class Name: DuelingDQN
Method Name: learn


Project Name: MorvanZhou/Reinforcement-learning-with-tensorflow
Commit Name: 673ef4c239a69b93f9fe388079af380c3ffa4ca4
Time: 2017-08-14
Author: morvanzhou@gmail.com
File Name: contents/5_Deep_Q_Network/DQN_modified.py
Class Name: DeepQNetwork
Method Name: learn


Project Name: MorvanZhou/Reinforcement-learning-with-tensorflow
Commit Name: 0f546db82bd5c161b1e8fb1aa46cebb28a2a3e80
Time: 2017-08-14
Author: morvanzhou@gmail.com
File Name: contents/5.1_Double_DQN/RL_brain.py
Class Name: DoubleDQN
Method Name: learn