[PYTHON] Verstärkungslernen 5 Versuchen Sie, CartPole zu programmieren?

import gym
env = gym.make('CartPole-v0')
for i in range(20):
    observation = env.reset()
    for t in range(100):
        env.render()
        action = 0
        if observation[2]>0:
            action = 1
        observation, reward, done, info = env.step(action)
        if done:
            print("Episode{} finished after {} timesteps".format(i, t+1))
            break
env.close()

Recommended Posts