import gym

def main():
    env = gym.make('CartPole-v1')
    env.render()
    obs = env.reset()
    reward = 0
    while True:
        obs, rew, done, _ = env.step(policy(obs))
        env.render()
        reward += rew
        if done:
            break
    print('Total reward of %f' % reward)

def policy(obs):
    if obs[2] < -0.012419 or obs[3] < -0.091290:
        return 0
    return 1

main()