Author: Graham Laight
Date: 01:19:50 07/30/03
Go up one level in this thread
On July 30, 2003 at 01:28:30, Walter Faxon wrote: >On July 28, 2003 at 04:21:41, Graham Laight wrote: > >>On July 27, 2003 at 16:29:21, Ricardo Gibert wrote: > >[snipped] > >>>L1 L1 R0 L0 L1 L1 R0 R1 L1 R1 L1 L1 R1 L0 R0 L1 L0 L1 L1 R1 L1 R0 R1 R1 L0 L0 L1 >>>L1 R0 R1 R0 R0 L0 R1 R1 L0 R0 L0 L1 L1 L1 L0 L0 L0 R1 L0 L0 R1 R0 >> >>There you go - you won 17 points in the 1st half of the game, but only 10 points >>in the 2nd! >> >>-g > > >Graham, a suggestion: > >If learning is the key, why not a game that really makes learning pay off? The >simplest way in "matching pennies" is to increase the value of each point as the >game continues. That is, you incrementally increase the penalty for >"exploration" vs. "exploitation". This can lead to meta-strategies where for >example you might at first deliberately play predictably (i.e., badly) in order >to punish programs that rigidly follow past statistics. > >I don't know what weight change formula might be best. Maybe several might be >tried. The "ultimate" of course is that the weight doubles with each guess. > >Or instead add a "doubling cube" a la backgammon. > >Wanna try double or nothing? > >-- Walter This is an excellent idea! My only fear is that this will lead to players deliberately playing badly in the first half of the game. Take care, -g
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.