Skip to content

Latest commit

 

History

5 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

Qhanoi_parallel

hanoi tower problem in Q learning (parallel version)

Credits

Base code credit to : https://github.com/khpeek/Q-learning-Hanoi/blob/master/hanoi.py

Parallel version inspired by:

Kretchmar, R. Matthew. "Parallel reinforcement learning." The 6th World Conference on Systemics, Cybernetics, and Informatics. 2002.

The implemention is a dumb version, time complexity is somehow huge.

Requirements

Python 3.6 since we are using asyncio

Experimental Results

alt text

The right part is the original version, you can see the left desends 10 times faster when we have 10 agents working at the same time.

About

hanoi tower problem in Q learning (parallel version)

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages