Author: William H Rogers
Date: 15:32:24 03/12/02
Go up one level in this thread
Thanks for the suggestion. I remember Don Daily writing once that he tested his program by letting it play matches from fixed starting positions, and then comparing the moves played before and after the eval change until a different move is played. If the new move is better, the eval change is good. It's a workable system, but it still requires human judgement. I'd ideally want something that can be more or less automated. Playing testmatches doesn't cut it; too much variance in the results to test small changes and too slow too. I have a testing system for search changes that is more or less automated, fairly accurate and reasonably fast. Constructing something similar for eval changes would be great, but I don't know it it's even possible. GCP It is very possible to create what you mentioned. It has been done before. I do not remember who did it, but they had a program that modified its own eval and then played a series of games. It the modifications caused the new version to win then they kept it otherwise they went on to make another change, etc.. You can also use a much stronger program like Crafty to analyze you moves to see what it thinks is the better one too. I do not know how to do it, but I have read that others have done it in the past. Don't give up. Bill
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.