Author: Robert Hyatt
Date: 15:14:33 05/24/00
Go up one level in this thread
On May 24, 2000 at 16:00:26, Peter Kappler wrote: >On May 24, 2000 at 09:14:51, Robert Hyatt wrote: > >>On May 24, 2000 at 02:25:40, Peter Kappler wrote: >> >>>On May 24, 2000 at 00:17:35, Robert Hyatt wrote: >>> >>>> >>>>The problem is that the only "old" evidence was self-play with varied depth. >>>>Which is probably not a good test, since small changes are often magnified in >>>>self-test play, while at other times small changes have no effect at all. >>>> >>> >>>This part confuses me. Why would self-play be inferior to a test suite? I >>>don't understand what you mean by "small-changes" above... >> >> >>The problem is this: If you add one small piece of information to one program, >>and that is the _only_ difference in the two programs, then you will see that >>piece of information influence the games _frequently_. Because one uses it >>and the other has no idea about it. >> > >But that's exactly the point of the experiment - to isolate and measure the >difference in playing strength from ply n to n+1. > >--Peter For a single program. yes. But does it translate to another program? No more than you can compare my N plies to someone else's M plies, in the same way. I don't see anything that says one program gets better quicker (or less quickly) than another as depth is increased (or decreased). That is very hard to measure.
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.