Author: Georg v. Zimmermann
Date: 05:53:31 11/19/00
Go up one level in this thread
> >>>I'm also curious about how Exchess decides what to tune after each loss. How >>>does it "know" what evalution scores to change? >>> > >Ah, this is the "Temporal Difference" learning stuff. It is all explained in >the Knightcap ICCJ articles. A simple explaination is that a small change is >made in each parameter... this change is tested to see how significant a change >it would have made in the final score for each position and that significance is >scaled by how close that position is to the end of the game... the significance >of the change is used to judge which parameters should be adjusted and by how >much. This sounds very interesting. Unfortunately I did not understand the learning code at all. Is there any place to get this "knightcap article" on the web ? If not, can you maybe give some more technical details about this algorithm or annotate the learning code ? That would be great, Georg v. Zimmermann
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.