import gym
env = gym.make('CartPole-v0')
env.reset()
for i in range(100):
    env.render()
    # Input:
    #   Force to the cart with actions: 0=left, 1=right
    # Returns:
    #   obs = cart position, cart velocity, pole angle, rot rate
    #   reward = +1 for every timestep
    #   done = True when abs(angle)>15 or abs(cart pos)>2.4
    obs,reward,done,info = env.step(env.action_space.sample())
env.close()