Re: [computer-go] CGOS Deflation or Self-Play delusion?

Don Dailey: <[EMAIL PROTECTED]>: >But FatMan is still 1800!I wonder if FatMan improved causing the >deflation? :-) FatMan-1 is running as was :). GNU Go's, gnugo-3.7.10-l10F and gnugo-3.7.11-l10F, are also getting lower, though I forgot to mention. They were close to 1800 but now 1739 an

Re: [computer-go] CGOS Deflation or Self-Play delusion?

Don Dailey wrote: >But FatMan is still 1800!I wonder if FatMan improved causing the >deflation? :-) Don, why don't you use MoGo as the second anchor? -- Yamato ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mail

Re: [computer-go] CGOS Deflation or Self-Play delusion?

Oh, how silly I am not understanding Don's humor :-( I think it's since cgos's rating system depends on the opponents you played with and the order of opponents you played with. On 2/3/08, [EMAIL PROTECTED] <[EMAIL PROTECTED]> wrote: > Isn't FatMan an anchor and has a fixed 1800 rating? > > On 2/3

Re: [computer-go] CGOS Deflation or Self-Play delusion?

Isn't FatMan an anchor and has a fixed 1800 rating? On 2/3/08, Don Dailey <[EMAIL PROTECTED]> wrote: > But FatMan is still 1800!I wonder if FatMan improved causing the > deflation? :-) > > - Don > > > Hideki Kato wrote: > > Hmm, mogo-pr-1core is also getting lower rating these days. It had >

Re: [computer-go] CGOS Deflation or Self-Play delusion?

But FatMan is still 1800!I wonder if FatMan improved causing the deflation? :-) - Don Hideki Kato wrote: > Hmm, mogo-pr-1core is also getting lower rating these days. It had > been over 2500, 2525 at max I remember, but is 2476 today. > > -Hideki > > Yamato: <[EMAIL PROTECTED]>: > >> Gi

Re: [computer-go] CGOS Deflation or Self-Play delusion?

Hmm, mogo-pr-1core is also getting lower rating these days. It had been over 2500, 2525 at max I remember, but is 2476 today. -Hideki Yamato: <[EMAIL PROTECTED]>: >Gian-Carlo Pascutto wrote: >>I'm not sure what to think about the following: >> >>Leela 0.3.0 vs Leela 0.3.7, 455 game match >>177 v

Re: [computer-go] CGOS Deflation or Self-Play delusion?

Gian-Carlo Pascutto wrote: >I'm not sure what to think about the following: > >Leela 0.3.0 vs Leela 0.3.7, 455 game match >177 vs 278 => +78 ELO points for Leela 0.3.7 > >CGOS rating > >Leela_0.3.0_1CPU 2335 >Leela_0.3.7_2CPU 2333 > >Hmm..but also > >Zen-0.9 2386 >Zen-1.0 2385

Re: [computer-go] February KGS bot tournament

Reminder - it's tomorrow; or for some of you, later today. Nick In message <[EMAIL PROTECTED]>, Nick Wedd <[EMAIL PROTECTED]> writes Registration is now open for this Sunday's bot tournament. This will use small boards, 13x13 for the Formal division and 9x9 for the Open. It will start at

[computer-go] CGOS Deflation or Self-Play delusion?

I'm not sure what to think about the following: Leela 0.3.0 vs Leela 0.3.7, 455 game match 177 vs 278 => +78 ELO points for Leela 0.3.7 CGOS rating Leela_0.3.0_1CPU 2335 Leela_0.3.7_2CPU 2333 Hmm..but also Zen-0.9 2386 Zen-1.0 2385 or more: Uct-200801122348 Uct-200801132334

Re: [computer-go] Selecting tree child objects, was Hydra theory (was Hybrid theory)

Harri Salakoski wrote: Hi such question that do you typically traverse all child objects or is there faster way to select explored node child object. I have concluded that it is not at least easy as multiple nodes uct values change each simulation so trying to keep biggest uct value in first in

Re: [computer-go] Selecting tree child objects, was Hydra theory (was Hybrid theory)

It's a shame a priority queue can't be used. But after each simulation, all sibling change together. - Don Harri Salakoski wrote: > Hi such question that do you typically traverse all child objects or > is there faster way to select explored node child object. > I have concluded that it is not

[computer-go] Selecting tree child objects, was Hydra theory (was Hybrid theory)

Hi such question that do you typically traverse all child objects or is there faster way to select explored node child object. I have concluded that it is not at least easy as multiple nodes uct values change each simulation so trying to keep biggest uct value in first in list is maybe too expen

Re: [computer-go] Scalability study suggestion

Hi Chuck, Thank you for your interesting suggestions.I have previously considered a system where the distribution is based on how many contestants. For instance if there are hundreds of players you would want to generate best of 5 or 6 or more, but if there were only 3 or 4 you might want be

Re: [computer-go] Scalability study suggestion

i agree with everything except for the seeding. it takes very few games (especially with the distribution you suggest) to get somewhat near the right spot. with 500-ish games being played per player, the initial time to get into the right place isn't unreasonable. keep in mind that if you totall

Re: [computer-go] Go board recap

Joshua Shriver wrote: For whatever reason my email grep'ing skills haven't spawns answers to a previously emailed question. In chess we have xboard/winboard. What clients do you recommend for linux for GTP playing? I recommend Quarry. /Gunnar ___ co

[computer-go] Re: Move Prediction and Strength in Monte-Carlo Go

Hello. Hi, >I would like to confirm your experiments: I have noticed already that >adding shapes of radius > 4 improves prediction a lot, but does not >improve playing strength (from progressive widening). I have not yet tuned progressive widening. This information is helpful for my experiment

[computer-go] Scalability study suggestion

I have been following the scaling study closely. Thanks for everyone for gathering such interesting data and especially to Don and the people donating computers. I have 2 suggestions that could help increase the amount of information gathered from all the CPU hours being used to play these game

Re: [computer-go] gtp two way

Joshua Shriver wrote: In addition to my previous email is there a cli based app for doing two way gtp based head on head competitions between two engines? The GNU Go distribution provides multiple twogtp scripts in the interface/gtp_examples directory. These are written in Perl, Python, and P

Re: [computer-go] Hydra theory (was Hybrid theory)

David Doshay wrote: > I looked up borda voting on Wikipedia. I did not know this was called > Borda voting, and it might be called a zeroth-order version of what I > am thinking. Rather than just take rank order from each, I intended to > try to include other metrics, for example, some measure of

[computer-go] gtp two way

In addition to my previous email is there a cli based app for doing two way gtp based head on head competitions between two engines? -Josh ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/

[computer-go] Go board recap

For whatever reason my email grep'ing skills haven't spawns answers to a previously emailed question. In chess we have xboard/winboard. What clients do you recommend for linux for GTP playing? -Josh ___ computer-go mailing list computer-go@computer-go.o

Re: [computer-go] Re: Move Prediction and Strength in Monte-Carlo Go

Hi, I would like to confirm your experiments: I have noticed already that adding shapes of radius > 4 improves prediction a lot, but does not improve playing strength (from progressive widening). Also, even worse than that, for a given set of features, the pattern urgencies computed by MM ar

Re: [computer-go] Transformation between KGS ratings and Elo

Le samedi 2 février 2008, Christoph Birk a écrit : > On Sat, 2 Feb 2008, Alain Baeckeroot wrote: > > 1800 is gnugo, so this puts top programs near 1k (2d for extreme > > mogo_18) this seems reasonable to me. > > Are you confusing 19x19 and 9x9? > The ELO/KGS table is for 19x19, while mogo_18 plays

Re: [computer-go] Hybrid theory

Le samedi 2 février 2008, terry mcintyre a écrit : > > Apologies for not quoting Don Dailey's text on Borda voting -- > yahoo is doing something truly awful with quoted text, for some reason. > It also break mail-thread, putting your post in uncorelated thread. Maybe switch to another mail ? ;-