Author: Don Dailey
Date: 15:29:52 12/08/97
Go up one level in this thread
>The evals are not the best score seen, rather they are the >score at the time crafty changed to the "solution" move. IE >it is possible/probable that at deeper searches, the score got >even better, but this gives an idea of what it saw at the time >it decided the solution move was best. Note that the time was >not recorded until it "held" the correct move from that time to >the end of the search (I gave a 4 min max)... Whenever we run problem sets for evaluating our chess program, we use the convention of recording NOT the solution time, but the time of solution iteration. So if it finds the solution on the 7th iteration we wait until the 7th iteration is completely searched and record this as our solution time. For us it seems to give much more consistant results. When we time other programs we use the same convention. This is more accurate because solution time will tend to be an "accident" of where the move happens to fall in the root move list. Also we noticed that if we ordered the root list more intelligently for picking up good positional moves, the programs tactical solution times were penalized even though the program was actually made a little stronger. A side benefit is that it is a fairly good rule for weeding out "accidental" solutions. -- Don
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.