Author: Ratko V Tomic
Date: 21:50:09 07/27/00
Go up one level in this thread
Well, you're unjust to Thorsten. The rating calculations extract very little data from each game, about 1.58 bits per game (i.e. log2(3)). On the other hand, each ply contains about 5-6 bits of data, or for a 100 ply game you have 500 bits of data produced. Hence the conventional rating tests based on the 3-way game result are very highly inefficient, they keep about 0.3 percent of info produced in game. The advantage of ratings to the more efficient information extractors (such as human brain) is that one can compute such rating without even knowing how to play chess. Another advantage is that they're not biased by human subjective judgment (the ratings may manifest other biases which reduce their predictive power, especially when extrapolating to a new opponent from a small number of earlier opponents). A human chess player likely extracts 100 times more info per game than the mechanical rating calculator, and the stronger the player the more info he can extract. This is all pretty obvious to anyone who actually plays against programs and thinks on every move. Even after a single serious game against a new program you have a pretty good idea whether it is stronger (against humans) than some older program you played earlier. One can also notice this extraction efficiency by thinking through or analyzing a game played between the two programs. This is especially true if you also observe program's output and evaluations from move to move.
This page took 0.02 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.