Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: brilliant post! Maybe comps should show margin of error with evalua

Author: Stuart Cracraft

Date: 13:28:06 01/03/06

Go up one level in this thread


On January 03, 2006 at 09:05:12, Brian Richardson wrote:

><snip>
>>
>>Indeed, Rybka already thinks in winning % rather than centipawns. It's just that
>>current GUIs expect centipawns, so this is what is output. (This may change.)
>>
>>(The only minor issue here is "distance to mate".)
>>
>
>Any chance you would be willing to post a formula estimating centipawns score
>calculated from winning percentage?
>
>Perhaps it something like
>f(x) = 1/(1+exp(-x/150))
>for graph see
>http://www.compute.uwlax.edu/calc/output/137500/
>
>or
>f(x) = (1+tanh(x*.33/100))/2
>http://www.compute.uwlax.edu/calc/output/137503/
>
>Thanks,
>Brian

Yes - that would be interesting.



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.