main.py 文件源码

def bot_play(mainDQN: DeepQNetwork, env: gym.Env) -> None:
    """Test runs with rendering and logger.infos the total score
    Args:
        mainDQN (DeepQNetwork): DQN agent to run a test
        env (gym.Env): Gym Environment
    """
    state = env.reset()
    reward_sum = 0

    while True:
        env.render()
        action = np.argmax(mainDQN.predict(state))
        state, reward, done, _ = env.step(action)
        reward_sum += reward

        if done:
            logger.info("Total score: {}".format(reward_sum))
            break