0f546db82bd5c161b1e8fb1aa46cebb28a2a3e80,contents/5.2_Prioritized_Replay_DQN/RL_brain.py,DQNPrioritizedReplay,learn,#DQNPrioritizedReplay#,262

Before Change

    def learn(self):
        if self.learn_step_counter % self.replace_target_iter == 0:
            self._replace_target_params()
            print("\ntarget_params_replaced\n")

        if self.prioritized:
            tree_idx, batch_memory, ISWeights = self.memory.sample(self.batch_size)

After Change

            action = np.random.randint(0, self.n_actions)
        return action

    def learn(self):
        if self.learn_step_counter % self.replace_target_iter == 0:
            self.sess.run(self.replace_target_op)
            print("\ntarget_params_replaced\n")

        if self.prioritized:
            tree_idx, batch_memory, ISWeights = self.memory.sample(self.batch_size)

Instances