Computer Go (..., Baduk, Weiqi)
I like to play Go (I'm ranked as 2k EGF at the time of writing this), but also programming and researching Go. :-). Here is some of the more interesting stuff I've already done.
- Pachi - Reasonably strong MCTS bot with simple codebase:
- Homepage
- Browse code / download
- Pachi: State of Art Open Source Go Program - Paper describing Pachi and some of its novel techniques:
- Autotest - framework for automated distributed performance measuring of stochastic engines
- sgf2gtp - simple converter of SGF files to sequence of GTP commands, useful for easy Go engine debugging
- UEC 2013 - Information Sharing in MCTS presentation - an opportunity for big ideas in Computer Go
- Master Thesis – Information Sharing in MCTS - detailed introduction to current Monte Carlo Computer Go techniques and Pachi, some original improvements
- ICGA Journal 2011/3 – Balancing MCTS by Dynamically Adjusting the Komi Value - paper investigating the effects of the dynamic komi technique in Computer Go.
- Computer Go 2010 – complete state of art overview - Long slideshow, SGF appendices
Please note that the presentation covers only the successful undertakings - it is heavily focused on the Monte Carlo approach (currently by far the most promising) and almost entirely omits other approaches tried in the past, such as alpha-beta/lambda/PN search + a lot of knowledge or Neural Network based players.
- Gostyle - Tool for pattern-based game corpus analysis,
together with Joe Moudrik
(very raw work-in-progress as of 2010-03-15):
- Browse code / download
- Pre-print of paper submitted to IEEE TCAIG: On Move Pattern Trends in Large Go Games Corpus - pdf dvi
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
- Slideshow Summary of the paper
- CGoban-h - Improved version of the KGS client (project page)
- Advanced Study Room on KGS - I wrote and run the ladder which automatically gathers played games from KGS, and like to sponsor various prizes for ASR league/ladder winners