example.py 文件源码

def run(self):
        observation = env.reset()
        for t in range(1000):
            env.render()
            print(observation)
            action = agent.act()
            observation, reward, done, info = env.step(action)
            if done:
                print("Episode finished after {} timesteps".format(t+1))
                break
            wx.Yield()

        env.monitor.close()

        print("Simulation completed\nWaiting for closing window..")