如何在Google Colab中渲染OpenAI Gym？

如何在Google Colab中渲染OpenAI Gym？

原文链接:

https://colab.research.google.com/drive/1flu31ulJlgiRL1dnN2ir8wGh9p7Zij2t#scrollTo=pdb2JwZy4jGj

install dependancies, takes around 45 seconds

下面两个必须要提前安装好，要不然只用pip安装是会报错的~

!pip install gym pyvirtualdisplay > /dev/null 2>&1
!apt-get install -y xvfb python-opengl ffmpeg > /dev/null 2>&1

吃豆人环境：Pacman Dependancies

!apt-get update > /dev/null 2>&1
!apt-get install cmake > /dev/null 2>&1
!pip install --upgrade setuptools 2>&1
!pip install ez_setup > /dev/null 2>&1
!pip install gym[atari] > /dev/null 2>&1

Imports and Helper functions

import gym
from gym import logger as gymlogger
from gym.wrappers import Monitor
gymlogger.set_level(40) #error only
import tensorflow as tf
import numpy as np
import random
import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline
import math
import glob
import io
import base64
from IPython.display import HTML

from IPython import display as ipythondisplay


from pyvirtualdisplay import Display
display = Display(visible=0, size=(1400, 900))
display.start()

"""
Utility functions to enable video recording of gym environment and displaying it
To enable video, just do "env = wrap_env(env)""
"""

def show_video():
  mp4list = glob.glob('video/*.mp4')
  if len(mp4list) > 0:
    mp4 = mp4list[0]
    video = io.open(mp4, 'r+b').read()
    encoded = base64.b64encode(video)
    ipythondisplay.display(HTML(data='''<video alt="test" autoplay 
                loop controls style="height: 400px;">
                <source src="data:video/mp4;base64,{0}" type="video/mp4" />
             </video>'''.format(encoded.decode('ascii'))))
  else: 
    print("Could not find video")
    

def wrap_env(env):
  env = Monitor(env, './video', force=True)
  return env

env = wrap_env(gym.make("MsPacman-v0"))
#check out the pacman action space!
print(env.action_space)
observation = env.reset()

while True:
  
    env.render()
    
    #your agent goes here
    action = env.action_space.sample() 
         
    observation, reward, done, info = env.step(action) 
   
        
    if done: 
      break;
            
env.close()
show_video()