CartPole-v0 which is OpenAI's gym.

gym-CartPole-v0-test.py

# -*- coding: utf-8 -*-

import gym
from gym import wrappers

env = gym.make("CartPole-v0")
env = wrappers.Monitor(env, './cartpole-experiment-1')
for i_episode in range(20):
    observation = env.reset()
    for t in range(100):
        env.render()
        # print(observation)
        # action. 0: left, 1: right
        action = env.action_space.sample()
        observation, reward, done, info = env.step(action)
        if done:
            print("Episode finished after {} timesteps".format(t+1))
            break