摘要: gym调用gym的调用遵从以下的顺序env = gym.make('x')observation = env.reset()for i in range(time_steps):env.render()action = policy(observation)observation, reward, done, info = env.step(action)if done: …… bre... 阅读全文
posted @ 2020-07-20 23:14 Tolshao 阅读(1660) 评论(0) 推荐(0) 编辑