Author: Uri Blass
Date: 15:29:31 03/10/04
Go up one level in this thread
On March 10, 2004 at 16:04:32, Dann Corbit wrote: >On March 10, 2004 at 14:41:47, Uri Blass wrote: > >>On March 10, 2004 at 14:23:29, Dave Gomboc wrote: >> >>>On March 09, 2004 at 16:05:15, Gian-Carlo Pascutto wrote: >>> >>>>Yet no top program does this, and they had a human correct it >>>>afterwards in Deep Blue. The conclusion should be obvious. >>> >>>Is that so? >>> >>>>If you can develop a *top level* evaluation function, better than >>>>good human tuning, solely on learning from a GM games database, >>>>you deserve an award. Nobody has succeeded before. >>> >>>Jonathan Schaeffer learned weights in Checkers [Chinook] without even using a >>>human games database (he used TD learning). The weights he tuned score 50% >>>against his hand-tuned code. >>> >>>I learned weights in Chess [Crafty] using 32k positions, hill-climbing an >>>ordinal correlation measure. It too scores 50% against the hand-tuned code. >> >>How many games and what time control? >>There is a difference if you score 50% with 2 games and with 2000 games? >> >>It is also possible that you get 50% against Crafty but less against other >>opponents. >> >> >>>Given Deep Sjeng's source code, I could zero its evaluation function weights, >>>and learn them from GM games to score 50% against the weights you have right now >>>too. >> >>You may be right but you cannot know about source code that you do not know. > >With his method, he will eventually reach a good result with any engine. >It uses generations, and discards the weaker ones absorbing the stronger ones. >After long enough waiting, it must become stronger. The question is how much time is long enough. It is clear that there is a way to find the best setting after enough time. Even the simple way of testing every possible setting can find the best setting if you only have 10^1000 years to wait. The point is that you do not have infinite time and I am not happy with improvement "after long enough waiting" when I do not know how long is long enough. The question is simply practical question and not theoretical. If you see improvement in Crafty thanks to Dave's method it means that his method has good chances also to help other engines. If you see improvement with more programs then it increase the hope that his method is going to work but I do not think that you can prove that it works for every program. Uri
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.