import matplotlib.pyplot as plt

%matplotlib inline

from IPython import display

#可视化函数：

def show_state(env, step=0, info=""):

    plt.figure(3)

    plt.clf()

    plt.imshow(env.render(mode='rgb_array'))

    plt.title("Step: %d %s" % (step, info))

    plt.axis('off')

    display.clear_output(wait=True)

    display.display(plt.gcf())

完整代码

#整体实例代码如下：

import matplotlib.pyplot as plt

import gym

%matplotlib inline

from IPython import display

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

observation = env.reset()

for _ in range(100):

# env.render()

    action = env.action_space.sample() # your agent here (this takes random actions)

    observation, reward, done, info = env.step(action)

    show_state(env, action, info)

if done:

    observation = env.reset()

env.close()