Don wrote: > The final step, which I don't personally support because I think it's > too restrictive but is also possible is to require these programs to be > deterministic. So you could SPECIFY the exact starting seed for a > random number generator as well as the specific method (or equivalent) > to be used to select moves randomly.
For a language shoot-out I think this suggestion solves the issues with randomness, without really losing anything (*). The big benefit it brings is that you can specify the exact result to expect. E.g. 10,000 play-outs, gives 5268 wins to white, average playout length of 110.2 moves. This stops people optimizing in ways that change the quality, and allows the results to focus on telling us which languages are best for implementing monte-carlo tree searches. Darren *: Creative ways to generate random numbers that actually alter the quality of play are likely to apply equally to all languages anyway. -- Darren Cook, Software Researcher/Developer http://dcook.org/mlsn/ (English-Japanese-German-Chinese-Arabic open source dictionary/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/
