-
Playing a game of Othello (Reversi) with deep-learning network agent.
-
The network structure and Monte Carlo tree search algorithm mimicks that of AlphaGo by DeepMind.
-
The network parameter was trained by data produced by self-play games from blank knowledge except the rule itself.
-
This program needs 'pygame', 'numpy', 'pickle' from PYPI.
-
This program does not use the known machine learning framework such as tensorflow, but it uses the python files adopted and modified from the book 'Deep Learning from Scratch' by Saito Goki.
-
I also adopted and modified python files of othello game from the book 'Invent your own computer game with python' by Al Sweigart.
-
Notifications
You must be signed in to change notification settings - Fork 0
shim212/othello
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Playing a game of Othello (Reversi) with deep-learning network agent.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published