def train(self, train_episodes=200):
        if args.train:
            for episode in range(train_episodes):
                total_reward, done = 0, False
                state = self.env.reset().astype(np.float32)
                while not done:
                    action = self.choose_action(state)
                    next_state, reward, done, _ = self.env.step(action)
                    next_state = next_state.astype(np.float32)
                    self.buffer.push(state, action, reward, next_state, done)
                    total_reward += reward
                    state = next_state
                    # self.render()
#---------------------------------------------------------------------------#
                if len(self.buffer.buffer) > args.batch_size:
                    self.replay()
                    self.target_update()
#---------------------------------------------------------------------------#
                print('EP{} EpisodeReward={}'.format(episode, total_reward))
                # if episode % 10 == 0:
                #     self.test_episode()
            self.saveModel()
        if args.test:
            self.loadModel()
            self.test_episode(test_episodes=args.test_episodes)