1_Cartpole_DQN_run_fucntion.py

1_Cartpole_DQN_run_fucntion.py

def run(self):
    for e in range(self.EPISODES):
        state = self.env.reset()
        state = np.reshape(state, [1, self.state_size])
        done = False
        i = 0
        while not done:
            self.env.render()
            action = self.act(state)
            next_state, reward, done, _ = self.env.step(action)
            next_state = np.reshape(next_state, [1, self.state_size])
            if not done or i == self.env._max_episode_steps-1:
                reward = reward
            else:
                reward = -100
            self.remember(state, action, reward, next_state, done)
            state = next_state
            i += 1
            if done:                   
                print("episode: {}/{}, score: {}, e: {:.2}".format(e, self.EPISODES, i, self.epsilon))
                if i == 500:
                    print("Saving trained model as cartpole-dqn.h5")
                    self.save("cartpole-dqn.h5")
                return
            self.replay()