whatever.py

import numpy as np
import gym
from gym import wrappers

env = gym.make('CartPole-v1')
env = wrappers.Monitor(env, '/tmp/cartpole-experiment-v1', force=True)

for i_episode in range(100):
    observation = env.reset()
    while True:
        action = np.argmax([0,observation[2] + observation[3]])
        observation, reward, done, _ = env.step(action)
        if done:
            break