【发布时间】:2021-12-29 11:57:43
【问题描述】:
大家好,我遵循了该教程 https://www.youtube.com/watch?v=hCeJeq8U0lo&list=PLgNJO2hghbmjlE6cuKMws2ejC54BTAaWV&index=2 训练 DQN 代理 一切正常
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))
现在我想使用 DQN 而不是随机选择,而不必这样做
dqn.test(env, steps=10)
类似 dqn.predict 但我没有在他们的文档中发现你能帮忙
【问题讨论】:
标签: python-3.x tensorflow reinforcement-learning openai-gym keras-rl