Author: Robert Hyatt
Date: 10:02:44 09/05/01
Go up one level in this thread
On September 05, 2001 at 12:15:37, Uri Blass wrote: >On September 05, 2001 at 07:53:50, guy haworth wrote: > >> >>In the Ken-Thompson-themed ICGA Journal (June, 2001), Ernst Heinz published his >>latest self-play experiment results. >> >>Engines with different guaranteed-depth(?)-parameters were pitted against each >>other. >> >>The matches of the experimetn (3,000 games each) suggest that: >> >> 12-ply was 84 ELO points better than 11 ply >> 11-ply was 92 ELO points better than 10 ply >> 10-ply was 115 ELO points better than 9 ply >> >>Fairly strong indications of decreasing returns from increasing search. No >>doubt a proper statistical analysis will follow. >> >> >>An extra ply seems to require 4-6 times the 'effective power', so a factor of 36 >>- if realised across the system - is only 2 plies. > >I know that the top programs of today have usually branching factor that is >close to 3 and not 4-6 so a factor of 36 is more than 3 plies. > >I also know that based on the ssdf results 70 elo per doubling the speed makes >more sense. > >70 elo per doubling means something like 110 elo per ply. >84 elo per ply when going from 11 plies to 12 plies seems to be wrong because >the programs in the ssdf games get deeper than 12 plies. > >Uri It is a mistake to take the results of program A playing itself at different depths, and then extrapolate from that to predict how program B will do at different depths. Those Elo differences are for program vs program, where the _only_ difference is the depth of the search. It doesn't mean that the deeper searcher could not be tuned better to get even better results. And it doesn't mean that the program doesn't have huge positional holes, since the program will not understand and exploit them anyway. It is "just interesting data". It can't be used to say there _is_ or _is not_ any "diminishing returns with respect to search depth" except for that one specific program.
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.