import gym

env = gym.make('CartPole-v1')



highest = 0

for e in range(20):
  observation = env.reset()
  point = 0
  print('='*50)
  print('episode', e, 'highest', highest)

  while True:
    env.render()

    action = 1 if observation[2] > 0 else 0
    observation, reward, done, info = env.step(action) # take a random action
    #print('observation', observation)

    point += reward
    print('point', point)

    if done:
      if point > highest:
         highest = point

      break