Skip to content

ss892714028/2048-DQN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 
 
 
 
 

Repository files navigation

2048

2048-AI

Reinforcement Learning (DQN) plays 2048

Currently, although not optimal, the DQNagent can consistanly perform better than a random agent (score of 1100 points). After only few hundreds of epochs of training, the DQNagent is able to consistantly get score of 2500 points and above.

Todo

Find optimal reward structure

Adjust hyper-parameters

About

2048-ReinforcementLearning-DQN

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages