> I used "dynamic komi" in the following "Rule 42" way. Starting point for > this internal artificial komi was a very high value (to compensate for > the handicap stones), typically 300.5 or 320.5 . > Then, always when the evaluation had climbed up to 42 % or higher, > dynamic komi was reduced by 50 or 30 or 20 (or 10 near the end), > until finally the true value of 0.5 was reached.
Hi Ingo, Very interesting. It sounds nicely mechanical, and easy for programmers to implement. I like how it should jump the komi down each time black makes the mistake you've been patiently waiting for. Do you think 58% would work well when playing black in handicap games? I've read all the responses and as it appears the bots get to play handicap games as both black and white on KGS all someone needs to do is implement it and see if their rating improves (*). Darren *: Is the KGS rating algorithm transparent? So you could exclude wins/losses in black handicap games, and white handicap games, and calculate the rating from even games only. Compare this to the main rating and you instantly know if the bots handicap play is its achilles heal or its speciality. -- Darren Cook, Software Researcher/Developer http://dcook.org/gobet/ (Shodan Go Bet - who will win?) http://dcook.org/mlsn/ (Multilingual open source semantic network) http://dcook.org/work/ (About me and my work) http://dcook.org/blogs.html (My blogs and articles) _______________________________________________ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/
