Open Infinity0106 opened 4 years ago
Before hand, Thanks you for all the knowledge that you have shared, if it was not for your videos I could not understand Q Learning.
https://github.com/philtabor/Youtube-Code-Repository/blob/3fd7b0248e3e81a75d889a80ed2bf7f710334b12/ReinforcementLearning/DeepQLearning/dueling_dqn_keras.py#L120
I tested with my code and apparently they do the same
q_next = np.squeeze(q_next) q_next[dones] = 0.0 q_tmporal = rewards + self.gamma*q_next q_target[np.arange(self.batch_size),actions] = q_tmporal
Before hand, Thanks you for all the knowledge that you have shared, if it was not for your videos I could not understand Q Learning.
https://github.com/philtabor/Youtube-Code-Repository/blob/3fd7b0248e3e81a75d889a80ed2bf7f710334b12/ReinforcementLearning/DeepQLearning/dueling_dqn_keras.py#L120
I tested with my code and apparently they do the same