Author: KarinsDad
Date: 08:26:42 10/15/99
Go up one level in this thread
On October 15, 1999 at 01:24:48, Ratko V Tomic wrote: > >>> These small effects will thus not add up coherently >>>into a winning strategy as they do in high level human play. >> >>Depends on the program. My current program design calls for long term plans >>where "undoing" previous plans must be justified by a tactical advantage. >>Basically, it will have multiple PVs and select it's PV based on how well it >>follows the current plan. Hence, your concept of random optimal moves should be >>minimized. >> > >Well, that's interesting. What's your program's name and is it a playing program >as yet? (I have a similar project, but it is still in its early infancy, much >more research oriented than for a practical play.) > The program is currently called Deflection. It plays around 1800-1900 strength (when it works), but it is still real simple right now. A lot of our pruning techniques, evaluation routines, and optimizations have not been implemented. And also, it does not do Alpha Beta, so we are doing a lot of work towards enhancing it's search engines (it has more than one). However, since we haven't found papers on any other program using our technique, we are sort of flying by the seat of our pants on this (who knows, it may not work well enough or fast enough). However, for some reason, it blows up in the extensions around 20 ply at the moment, so we still have work to do, just to get it working again. Currently, it does not yet have the plan pre-processor or plan post-processor working. Those ideas are only in the design spec. We want to get a good 2200-2300 level program working before we start worrying about the planning portion. And, we are far from implementing an opening book, GUI, or tablebases. KarinsDad :)
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.