真实角角rl DQN预测

Question

大家好，我遵循https://www.youtube.com/watch?v=hCeJeq8U0lo&list=PLgNJO2hghbmjlE6cuKMws2ejC54BTAaWV&index=2教程来训练DQN代理，一切都很好

env = gym.make('CartPole-v0')
states = env.observation_space.shape[0]
actions = env.action_space.n

episodes = 10
for episode in range(1, episodes+1):
    state = env.reset()
    done = False
    score = 0 
    
    while not done:
        env.render()
        action = random.choice([0,1])
        n_state, reward, done, info = env.step(action)
        score+=reward
    print('Episode:{} Score:{}'.format(episode, score))

现在，我不想做随机的选择，我想使用DQN而不必去做

dqn.test(env, steps=10)

类似dqn.predict的东西，但我在他们的文档中找不到，你能帮上忙吗

Answer 1

dqn.forward(state)

它在其github repo https://github.com/taylormcnally/keras-rl2/blob/master/rl/agents/dqn.py中的测试代码中具有相同的功能。