OpenAI Gym 库使用小技巧

less than 1 minute read

Published:

OpenAI Gym 库使用小技巧。

gym 库渲染显示

1、使用虚拟帧缓冲区打开 notebook

xvfb-run -s "-screen 0 1400x900x24" jupyter notebook

2、实现在 notebook 中显示 gym 库的渲染显示

import matplotlib.pyplot as plt
%matplotlib inline
from IPython import display

def show_state(env, step=0, info=""):
    plt.figure(1)
    plt.clf()
    plt.imshow(env.render(mode='rgb_array'))
    plt.title("Step: %d %s" % (step, info))
    plt.axis('off')
    
    display.display(plt.gcf())
    display.clear_output(wait=True)

gym 库列出所有环境

# copy from https://github.com/openai/gym/blob/master/gym/envs/__init__.py
from gym import envs
envids = [spec.id for spec in envs.registry.all()]
for envid in sorted(envids):
    print(envid)

使用某个环境

import gym
env = gym.make('CartPole-v0')

参考资料及致谢

OpenAI Gym

How to run OpenAI Gym .render() over a server