[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Bug-gnubg] Re: Some questions & comment about contacting me

From: Achim Mueller
Subject: [Bug-gnubg] Re: Some questions & comment about contacting me
Date: Thu, 27 Nov 2003 22:36:37 +0100
User-agent: Mutt/1.5.4i

* Thomas Hauk wrote on 26 Nov 2003:

> Sorry Achim, I missed your question:
> > Just one question: What is this thesis for?
> mainly because I do not subscribe to the gnubg mailing list, just because 
> there's too much discussion about stuff that isn't code-related for me to 
> really care about. That doesn't mean I don't want to answer your questions 
> (although you did mention something contrary to that to my supervisors in 
> Graz!), just that you'll have to remember to CC: me at 
> <address@hidden> so I can respond. 8)

That's ok, I didn't want to be unkind when talking with Michael. I
only wondered why you seemed to ignore my question.

> At this point we haven't seen a great deal of improvement in deep search 
> -- perhaps no improvement, really -- but I am continuing my work 
> nonetheless.
> Have any of you done any benchmarking, playing gnubg versus itself, using 
> different ply settings? Say, gnubg at 0-ply versus gnubg at 1-ply or 
> 2-ply? Have you seen statistically significant differences?

> I am running DMP games right now, as my search algorithms do not yet 
> handle the cube. Any thoughts on that?

I know that you did a long simulation of (what we call) 0ply vs 1ply
(or was it 2ply) and you wondered, that there was nearly no difference
in playing strength. Michael told me that you were playing
1-pointers without cube and gammons. I think that the real skill of
gnubg shows up when you play short matches with cube. You may ask
Joesph Heled if he has some statistic material for different plies
(I bet he has), but I think there is not much difference in checker
play only.

The matches in Graz showed, that there was nearly no difference in 
checker play between the two bots gnubg and bgblitz, but miles in cube 
handling. A few examples will follow later this week, I'm just rolling 
out dozends of positions from the five matches.

I plan to start a longer simulation of match plays here at work
(<whisper> have to look for some forgotten 2-CPU servers</whisper>),
but I will only change the match equity tables. The simulation will
last a while, because the two gnubgs will play 2ply. I estimate 8-12
minutes for a match and want to play 10.000 (means  ~ 2 months if all
goes well).



achim mueller, anne-frank-str. 25, D-48431 rheine
+49 (0)5971 83767, +49 (0)163 8458340
pgp/gnupg key: 1024D/5DF3A722 (wwwkeys.de.pgp.net)

Attachment: pgp6gRpm6IdzA.pgp
Description: PGP signature

reply via email to

[Prev in Thread] Current Thread [Next in Thread]