Author: Dave Gomboc
Date: 18:05:40 03/16/04
Go up one level in this thread
On March 16, 2004 at 06:32:55, Steven Edwards wrote: >A few points on the 1800 Elo number in the primary goal set: > >1. The only test suite data we have for Paradise is just under a hundred >positions from the first one hundred positions from WAC. I think its >performance was somewhat under 2000 Elo because of its time limit of forty-five >minutes per move, and that is one reason for the 1800 Elo figure in the primary >goal set. 45 minutes on a machine from 20 years ago is about how long, on today's hardware? Three seconds. Besides, IIRC, Wilkins only gave it that kind of time because it was being interpreted as it ran. Your stuff will be compiled, or at least JIT-compiled, won't it? >2. A second reason for the 1800 Elo figure is that I suspect that, unlike the >case with most programs, incremental improvement is going to be strongly >correlated with the chess skill of the improver (me). I haven't played OTB >chess in some 20 years and I don't think I could do much better than 1800 if I >were to try it today. This is a serious consideration. I guess my off-hand reply is that assuming you get something working, it will be much easier for chess-playing friends who are stronger than you to explain what reasoning to add, or even add it themselves. The ability to easily integrate human knowledge is a major point of the exercise, yes? >3. The third reason for the 1800 number is how I would like to get the rating: >from OTB USCF tournaments. The human player distribution is such that there >would be a lot more confidence in the target number when the number is within >two sigma of the mean and not four (or more) away. >4. A difficulty here is getting any kind of an OTB rating. To my knowledge, >there haven't been any "computers allowed" USCF events in my area for a long >time. There were a good number back in the late 1980s when I deployed my >program Spector, but not today. My idea here is to get some local TDs to allow >computer entry by helping to sponsor a prize fund, and this might be a budget >breaker. (Note: this is the reason for the caveat in #18 and #19.) Now even I think you're dreaming! ;-) Either that, or you'll be organizing a lot of tournaments yourself. In most cases, you could bring your program in on a hand-held and a director will refuse it entry. You might be able to swing it if you're an active chess player yourself -- people would be less hostile to a program written by their friend (or at least acquaintance). (Incidentally, I'm not a gambler and will not be taking either side of the wager!) Dave
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.