Skip to content

Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using MXNet)

Notifications You must be signed in to change notification settings

z01nl1o02/DRL-FlappyBird

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Reference

DRL-FlappyBird

todos

re-implemented with gluon

#usage

  • train from starting
    python FlappyBirdQDN.py
  • train with one checkpoint (with 3w+ timestep) python FlappyBirdQDN.py traind.params

results

  • smart bird comes after about 2w steps
  • Block converages quickly than HybridBlock? bird (HybridBlock) show smart after 3w steps

About

Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using MXNet)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • Python 100.0%