Re: [computer-go] Intelligence

Hi Erik, Erik van der Werf: <[EMAIL PROTECTED]> >IMO the adaptation is just a means to an end. The end (Intelligence, >whatever it is) does not necessarily require adaptation. I used to think learning is required for intelligence but recently I'd like to propose some creativity is. Hideki (gg)

Re: [computer-go] Intelligence

lve a problem. Hideki Weimin Xiao: <[EMAIL PROTECTED]>: >I would believe the creativity is implied in learning. > >Weimin > >- Original Message - >From: "Hideki Kato" <[EMAIL PROTECTED]> >To: "computer-go" >Sent: Sunday, July 22, 2007

Re: [computer-go] Intelligence

Jacques Basaldúa: <[EMAIL PROTECTED]>: >Hideki Kato wrote: > >> Creativity here is, to generate a new method by combining methods >> the system already has, in order to solve a problem. > >That is creativity for the job of designing algorithms. Playing >go, creativity

[computer-go] GGMC Go v1.3

http://www.gggo.jp/ggmc-v1.3.tar.gz (~200kB) Hideki (gg) -- [EMAIL PROTECTED] (Kato) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] GGMC Go v1.3

Rémi Coulom: <[EMAIL PROTECTED]>: >Martin Møller Skarbiniks Pedersen wrote: >>> http://www.gggo.jp/ggmc-v1.3.tar.gz (~200kB) >>> >>> >> >> DNS problems ? >> >> Resolving www.gggo.jp... failed: Temporary failure in name resolution. >> ___ >> computer-

Re: [computer-go] GGMC Go v1.3

Rémi Coulom: <[EMAIL PROTECTED]>: >Hideki Kato wrote: >> http://www.gggo.jp/ggmc-v1.3.tar.gz (~200kB) >> >> Hideki (gg) >> -- >> [EMAIL PROTECTED] (Kato) >> ___ >> computer-go mailing list >>

Re: [computer-go] GGMC Go v1.3

Rémi Coulom: <[EMAIL PROTECTED]>: >Hideki Kato wrote: >> Rémi Coulom: <[EMAIL PROTECTED]>: >> >>> Hideki Kato wrote: >>> >>>> http://www.gggo.jp/ggmc-v1.3.tar.gz (~200kB) &

Re: [computer-go] Re: 9x9 games wanted

Hi elife, The records are of komi 6.5. If it's OK, I'll ask Mr. Okasaki to permit. Hideki (gg) elife: <[EMAIL PROTECTED]>: >Hi gg, > > Are this database available now? I would like to use it to train my 9x9 >bot. > >Best Regards > > >On 7/

[computer-go] A Japanese translation of MoGo paper at ICML07

Hi all, this might be meaningless besides Japanese, You can download a Japanese translation of MoGo paper at ICML07, http://www.geocities.jp/hideki_katoh/387.jp.pdf (685 kB). Incidentally, a Japanese translation of the first report on Crazy Stone (CG2006.pdf), http://www.geocities.jp/hideki_kat

[computer-go] Re: Congratulations to GNU Go!

Hi Nick. Thank you for origanizing such nice tournaments every month. First, you'd better to remove trailing period from URL. It lead me to "404 Not Found" error :). It was just my guess that the cause of MoGo's reapeated crash is of the code of gc. Rather, I agreed later the bug is in scori

[computer-go] Re: Binary release of MoGo

Sylvain Gelly: <[EMAIL PROTECTED]>: >Unfortunately, only the linux version is available (for the moment?). >I wanted to wait for the windows version to be available at the same >time, but it is 2 times slower than the linux version(!!), so I >decided not to distribute it for the moment. I use cygw

Re: [computer-go] Re: Binary release of MoGo

Sylvain Gelly: <[EMAIL PROTECTED]>: >> Try MinGW (and MSYS). MinGW has GCC ver. 4.2.1. >> http://sourceforge.net/project/showfiles.php?group_id=2435 > >Yes, I saw that and tried. But the thing is that MoGo use pthread >library for multitreading, and, as far as I know, MinGW does not >provide pthr

Re: [computer-go] Re: Binary release of MoGo

Sylvain Gelly: <[EMAIL PROTECTED]>: >> BTW, MoGo doesn't work well with gogui 0.9, Fedora Core 5 and Core 2 >> Quad system. >Really? Argh :'( > >> 00:00 1 name >> tried to open opening, success 0<-- in grey >Here it does not find the file, because the file is with the binari

Re: [computer-go] Re: Binary release of MoGo

Sylvain Gelly: <[EMAIL PROTECTED]>: >> >> tried to open opening, success 0<-- in grey >> >Here it does not find the file, because the file is with the binaries >> >and gogui (at least your version) looks into the gogui/bin directory. >> >But that does not prevent MoGo to wor

Solved! Re: [computer-go] Re: Binary release of MoGo

It's just setting of Gogui. When I turned off the auto-number feature, mogo worked fine. # Settings -> Configure Shell -> Auto number Cheers, Hideki Sylvain Gelly: <[EMAIL PROTECTED]>: >> I guess the search path you've coded is something wrong or different >> depends on the distributions. >The

[computer-go] Re: Tesuji

Hi Shriver, Tesuji is really a Japanese word. "Te" means a hand or a move and "suji" means a line or a sequence. So, "tesuji" means a sequence of good moves, in general. Usually used for some particular sequences like what you can see at . Hope this helps, gg

[computer-go] Re: Tesuji

Tesuji is also used for the first move of such sequence of moves. -gg Hideki Kato: <[EMAIL PROTECTED]>: >Hi Shriver, > >Tesuji is really a Japanese word. "Te" means a hand or a move and >"suji" means a line or a sequence. So, "tesuji" means

Re: [computer-go] Binary release of MoGo

Hi Sylvain, Some computer-go friends in Japan have reported that even current binary of MoGo doesn't work on Athlon XP or Celeron. Both (and Pentium III) have no SSE2 instructions while Pentium 4 has. Could you please try -march=athlon-xp, pentium3 or generic? Hideki Sylvain Gelly: <[EMAIL P

[computer-go] Re: Update of MoGo binary release, and windows version available!

Hi Sylvain, Thank you for the releases of the Windows version and the Linux version for older processors. The Windows version, however, seems much weaker than MoGo that running on KGS these days on 19x19, even giving much longer time setting such as "--time 300" for example. I guess some othe

Re: [computer-go] IEEE Spectrum article by Deep Blue creator

David Fotland: <[EMAIL PROTECTED]>: >Many Faces does not use null move, but does extensive caching of life and >death and other tactical results. The problem of such caching scheme is when and how programs can make correctly the cache be dirty (ie, invalid). It may be very hard even for human p

[computer-go] So many MoGo run on cgos 9x9

Hi Don and all, There are many variants of MoGo run on CGOS 9x9 now # http://cgos.boardspace.net/9x9/standings.html I guess they force confuse the rating system because MoGo is the strongest, programs have a match more frequently against MoGo than anchors and get rating decrease in average.

Re: [computer-go] So many MoGo run on cgos 9x9

d we could even >adjust it later based on more games.) Don't you try the same for high-end anchor using released version of MoGo? -gg >- - Don > > >Hideki Kato wrote: >> Hi Don and all, >> >> There are many variants of MoGo run on CGOS 9x9 >> now #

Re: [computer-go] So many MoGo run on cgos 9x9

Hi Olivier, Thanks a lot. (^^)/ # A Japanese face mark. Smiling with left hand up. No need to rotate your head, like this :-). -gg Olivier Teytaud: <[EMAIL PROTECTED]>: >>> There are many variants of MoGo run on CGOS 9x9 >>> now # http://cgos.boardspace.net/9x9/standings.html > >Hello all; >

Re: [computer-go] So many MoGo run on cgos 9x9

Hi Olivier, Thanks a lot. (^^)/ # A Japanese face mark. Smiling with left hand up. No need to rotate your head, like this :-). -gg Olivier Teytaud: <[EMAIL PROTECTED]>: >>> There are many variants of MoGo run on CGOS 9x9 >>> now # http://cgos.boardspace.net/9x9/standings.html > >Hello all; >

Re: [computer-go] So many MoGo run on cgos 9x9

Hi greenpeep aka chris, My program GGMC Go ver. 2, rated around 2000 ELO now, runs abut 25k playouts/s on 4-core box and do 360k playouts/move at most on cgos (and last KGS tournament as well). It's based on MoGo's first report, though its framework is different. # I'll add some features but h

[computer-go] Re: Hakone 2007

The Workshop itself is usual but we have a local computer-go tournament as a night event this year (and possibly following years). -Hideki Darren Cook: <[EMAIL PROTECTED]>: >Rémi wrote: >> I'll connect Crazy Stone after the tournament in Hakone >> (mid november). > >Is it a tournament or the usua

Re: [computer-go] 19x19 CGOS

I prefer shorter time control. The object I use cgos is to measure my program's performance against other programs. Cgos is not a tournament in any sense. It should be a tool for developers, I believe. Then, fairness is not so important because I can estimate my program's performace at longe

Re: [computer-go] 19x19 CGOS

Did you give "--capture-all-dead" to gnu? -hideki David Fotland: <[EMAIL PROTECTED]>: >10 minutes is slightly too fast for Many Faces full strength. It plays most >of the game at level 10, then drops down. > >Also, the gnugo 10 that's fixed at 1800 doesn't remove dead stones, so the >score is of

Re: [computer-go] 19x19 CGOS

Hi all, Jeff Nowakowski: <[EMAIL PROTECTED]>: >On Sun, 2007-10-28 at 11:54 +0100, Edward de Grijs wrote: >> >> >> Hi all, >> >> For CGOS 19x19 I prefer a short time control (10min/game) because: >> >> 1) More quickly a more accurate rating can be established. > >I agree with Don. 10 minute

Re: [computer-go] 19x19 CGOS

Don Dailey: <[EMAIL PROTECTED]>: > >> About fairness, as classical programs including GNU Go and ManyFaces >> need about ten minutes for their best performace, why do you give >> other (Monte Carlo) programs thirty minutes? >> >> >What time control do they use in serious tournaments?Do yo

Re: [computer-go] CGOS 19 TC

Hi Don, Thanks very much for your effort to work cgoses. I'd like to support your idea and expect you will implement it. -Hideki Don Dailey: <[EMAIL PROTECTED]>: >My thoughts are that it would fragment the players, we would get much >less activity on either server and we need lot's of variety

Re: [computer-go] cgos viewer feature request

Hi Don, Thank you for the additional feature. It seems, however, strange. Does 04:19 mean 41.9 seconds? Hideki Don Dailey: <[EMAIL PROTECTED]>: >I just updated the current viewer to version 0.35. > >I added the remaining time display. > >The default server is the 19x19 server, so if you use it

Re: [computer-go] cgos viewer feature request

Hi Don, Don Dailey: <[EMAIL PROTECTED]>: > > >Hideki Kato wrote: >> Hi Don, >> >> Thank you for the additional feature. >> >> It seems, however, strange. Does 04:19 mean 41.9 seconds? >> >> Hideki >> >Hi Hideki, > >04:19

Re: [computer-go] cgos viewer feature request

Hi Don, Now I understand the time is the time left! So your code is not wrong (_ _). # A Japanese facemark that means I'm sorry. Don't rotate your head. Hideki Hideki Kato: <[EMAIL PROTECTED]>: >Hi Don, > >Don Dailey: <[EMAIL PROTECTED]>: >> >> >

Re: [computer-go] cgos viewer feature request

k by subtraction with the previous entry >than it is to see how much time is left by adding up every entry. > >- Don > > >Hideki Kato wrote: >> Hi Don, >> >> Now I understand the time is the time left! So your code is not >> wrong (_ _). >>

[computer-go] Re: Computer Go tournaments - various

ve any results >from these events? The result of GPW 2007 Cup* at Hakone on 9-10 Nov was: Pos Program Developer HardwareWin Games 1 Crazy Stone Rémi Coulom Intel 4 x 1 Q6600 3GHz 10 10 2 GGMC Go Hideki Kato Intel

[computer-go] Re: Computer Go tournaments - various

uter Go side-event. Does anyone have any results >from these events? The result of GPW 2007 Cup* at Hakone on 9-10 Nov was: Pos Program Developer HardwareWin Games 1 Crazy Stone Rémi Coulom Intel 4 x 1 Q6600 3GHz 10 10 2

[computer-go] Re: Great day for CrazyStone!

Congratulations, Rémi! The official page of UEC Cup is and the result will be (in preparing). Hideki Ian Osgood: <[EMAIL PROTECTED]>: >According to computer-go.info, today CrazyStone won both sections of >the KG

Re: [computer-go] New engine? From a Chess programmer perspective.

Hi all, Gian-Carlo Pascutto: <[EMAIL PROTECTED]>: >> On Sun, 2 Dec 2007, Russell Wallace wrote: >>> I haven't seen Leela before, but the claim of high dan-level >>> performance on 9x9 is certainly interesting. >> >> I don't think 2200 ELO on the 9x9 CGOS is equivalent to 'high dan-level' >> play.

Re: [computer-go] Re: Update of MoGo binary release, and windows version available!

Adding "quit" does not help? Edward de Grijs: <[EMAIL PROTECTED]>: > > > >Hi to all, > >Can someone help me with this problem, for which I cannot >find a solution: >I am trying to run MoGo in an automatic way, using the >cygwin toolkit. >The problem in its simplest form is this: >If I use MoGo o

Re: [computer-go] Re: Update of MoGo binary release, and windows version available!

Hi Edward, Edward de Grijs: <[EMAIL PROTECTED]>: > >Hi Hideki, > >The file is used by: >cat file | mogo I guess MoGo doesn't check end-of-file of stdin. >Adding quit to the file lets mogo quit the game, but >I want to let mogo wait for the obvious next command like >play b Then, you can mak

Re: [computer-go] Re: Update of MoGo binary release, and windows version available! (repost)

Hi Edward, Edward de Grijs: <[EMAIL PROTECTED]>: > >Hi Hideki, > >The file is used by: >cat file | mogo I guess MoGo doesn't check end-of-file of stdin. >Adding quit to the file lets mogo quit the game, but >I want to let mogo wait for the obvious next command like >play b Then, you can mak

Re: [computer-go] Re: Update of MoGo binary release, and windows version available! (repost)

Edward de Grijs: <[EMAIL PROTECTED]>: > > >Thanks Hideki, Chris and Jacques for your replies. > >> Hideki wrote: >> Then, you can make a very simple program that passes a file to stdout >> first and passes stdin to stdout after the end-of-file of the file. >> And use it as "a.out file | mogo ". >I

Re: [computer-go] Hall of fame for CGOS

Hi Don, Thank you for giving us such an excellent Xmas present. One question, why the rating of FatMan-1 is not 1800? And, I'll be happier if there are links to programs on HOF so that I can see their rating pages. Hideki Don Dailey: <[EMAIL PROTECTED]>: >I want to clarify this: > >The new CGO

Re: [computer-go] low-hanging fruit - yose

Hi Gunnar, Gunnar Farnebäck: <[EMAIL PROTECTED]>: >Heikki Levanto wrote: > > On Mon, Dec 10, 2007 at 04:08:48PM -0500, Don Dailey wrote: > >> Would you rather be 95% confident of a win or 90% confident?There is > >> only 1 correct answer to that question. > > > > Yes, if you can offer me relia

Re: [computer-go] Where and How to Test the Strong Programs?

Hi Don, There are not enough evidence to believe this. Tast-3k has too few matches against each program, less than ten games and has no matches against strongest programs including Crazy Stone, MoGo and greenpeep. In addition, there seems some bias, that is, his winning rate against gnugo-3.7

Re: [computer-go] Where and How to Test the Strong Programs?

Hi Rémi , Rémi Coulom: <[EMAIL PROTECTED]>: >Don Dailey wrote: >> It would be great if you would provide recommendations for a simple >> conversion formula when you are ready based on this study. Also, >> if you have any suggestions in general for CGOS ratings the >> cgos-developers would be

Re: [computer-go] low-hanging fruit - yose

Hi Begué and Don, I did this in my earlier version of ggmc. The real code was: reward = 0.5 * (1 + tanhf(K * (score - komi))); # tanhf() is a float, not double, version of hyperbolic tangent function. # I use tanh() as exp() may cause overflow. # You can see the code from http://www.gggo.jp/ as

Re: [computer-go] Hall of fame for CGOS

Hi Don, Don Dailey: <[EMAIL PROTECTED]>: >I want to clarify this: > >The new CGOS chart uses bayeselo to recalculate all the ratings for the >players - it does not use CGOS ratings. Hm, now I remembered that there were not so few games wrongly ended and scored by server's hang-up. In addition, r

Re: [computer-go] Hall of fame for CGOS

r that.It's the same if you lose your connection and >lose on time as a result.It's part of your "equipment", it's as if >you had automobile failure at the Nascar races or your tennis racket >breaks during an important point. > >- Don > > >

Re: [computer-go] Hall of fame for CGOS

We have to announce and make sure almost all perticipants won't do it. Yes, network troubles are out of our control, some other troubles and/or accidents will happen. That's why we have to have some experiments before using the name of 'Hall of fame'. -Hideki Don Dailey: <

Re: [computer-go] Hall of fame for CGOS

ery month. > >Also, there is no "Hall of Fame." It's only a list to show ALL >players over time and it uses bayeselo instead of the standard CGOS elo >system (which doesn't change.) > >- Don > > > > >Hideki Kato wrote: >> Your senten

Re: [computer-go] Hall of fame for CGOS

. I wanted to just postpone the use of the name "HoF" until we confirm the overall ratings are correct enough to use the name. Don, please remove my bots, ggmc-xxx, from your HoF if possible. I'd like to apologize to all. -Hideki Chris Fant: <[EMAIL PROTECTED]>: >On Dec

Re: [computer-go] Hall of fame for CGOS

ignore lower-rated versions that may represent >experiments, buggy prototypes, and the like. I was afraid also that outsiders may evaluate the ranking at HoF too much by its name. Finally, I'd like to thank Don, Eric, Chris and other subscribers of this list and apologize to for my po

[computer-go] Re: OpenMP / Quad Core experiments

Happy New Year, all. terry mcintyre: <[EMAIL PROTECTED]>: >I have been tinkering with OpenMP and my new HP Quad >Intel 6600. Wrote a small program to compute the >Taylor series of e and pi, just for exploration, and >I've found some interesting data points. > >I am using gcc 4.2 and 4.3.1 - the la

[computer-go] Re: OpenMP / Quad Core experiments (repost)

Happy New Year, all. terry mcintyre: <[EMAIL PROTECTED]>: >One more puzzle: this processor is rated at 2.4GHz, >but cpuinfo tells a different story: It's because SpeedStep is working. You can stop it in BIOS setting. http://en.wikipedia.org/wiki/SpeedStep -Hideki >[EMAIL PROTECTED]:/proc$ cat

[computer-go] Re: Please have your bot resign, for your own good

Hi Peter, Following is my (Tokyo, Japan) data. Tough I'm not familiar with network, the latency seems greater than 250 ms, right? -Hideki $ tracepath 208.100.19.102 1: 192.168.1.100 (192.168.1.100) 10.849ms 2: softbank219186009254.bbtec.net (219.186.9.254)7

[computer-go] Re: MoGoRel3_3550pps

I use, mogo --9 --totalTime 300 --nbThread 1 --pondering 1 --playsAgainstHuman 0 for mogo-pr-1core and mogo --9 --nbTotalSimulations 1 --nbThread 1 --pondering 1 --playsAgainstHuman 0 for mogo-pr-10k on cgos 9x9. I guess "--playsAgainstHuman 0" is missing. -Hideki Michael Williams: <[EMAIL

Re: [computer-go] Re: MoGoRel3_3550pps

uman... :( Be careful. Japanese has no plural nor third person singular variations... -Hideki >Hideki Kato wrote: >> I use, >> mogo --9 --totalTime 300 --nbThread 1 --pondering 1 >> --playsAgainstHuman 0 >> for mogo-pr-1core and >> mogo --9 --nbTotalSimulations 100

Re: [computer-go] handicap for mogo against pro ?

Gian-Carlo Pascutto: <[EMAIL PROTECTED]>: >Olivier Teytaud wrote: > >> Also, there are probably other people interested in combining >> UCT and mpi; I don't know if some people have a more precise idea >> of the level of the MPI+UCT combination than us. Someone ? > >MPI is just a parallel programm

Re: [computer-go] handicap for mogo against pro ?

Gian-Carlo Pascutto: <[EMAIL PROTECTED]>: >Hideki Kato wrote: > >> No. Remember UCT is a sequential algorithm. Parallelizing UCT make >> playouts ineffective. Increasing the number of threads and/or >> communicating delay decreases the effectiveness of the play

Re: [computer-go] handicap for mogo against pro ?

Gian-Carlo Pascutto: <[EMAIL PROTECTED]>: >Hideki Kato wrote: > >> What is "correct" move? It has sense only for some artificial >> problems or very limited positions, and so, it cannot evaluate total >> performance of a program. >> > >This

Re: [computer-go] handicap for mogo against pro ?

I don't think such positions are enough to evaluate "total" performance of a program. Because they don't include middle games nor opening games, for examples. -Hideki terry mcintyre: <[EMAIL PROTECTED]>: > > >Hideki Kato wrote: > >> What is

Re: [computer-go] Suicide question

Hi Don, I'm now running mogo-pr-1cpu on my quad core box, Intel Q6600 3GHz with 4GB RAM and gnugo-3.7.11-l10F, gnugo-3.7.10-l10F and FatMan-1 on an AMD athlon64 2GHz with 1GB RAM, as reference programs on cgos 9x9. I can provide these two boxes for your experiment. Then, how long will it tak

Re: [computer-go] Suicide question

ourse you can use "nice" to run these at low priority. > >Are you willing?I can send you a test package now which will >determine if it will run without hassle. > >- Don > > > > >Hideki Kato wrote: >> Hi Don, >> >> I'm now running mogo-

Re: [computer-go] Suicide question (Repost)

ourse you can use "nice" to run these at low priority. > >Are you willing?I can send you a test package now which will >determine if it will run without hassle. > >- Don > > > > >Hideki Kato wrote: >> Hi Don, >> >> I'm now running mogo-

Re: [computer-go] Suicide question (Repost)

on my core 2 duo. > >I will have an automatic update soon. Hopefully by tonight but I will >be in and out today and probably won't be able to work on it for a while. > >- Don > > >Hideki Kato wrote: >> Yes, Fedora Core 5-64bit for AMD and Ubuntu 7.10-64bit for Intel. >

Re: [computer-go] New scalability study progress report

Don Dailey: <[EMAIL PROTECTED]>: >FatMan uses a fixed memory allocation and I think Mogo does too so I >don't even have a simple way to know how much memory FatMan is >"effectively" utilizing. Just as info, MoGo allocates memory dynamically. I saw it via "top" command on Linux. -Hideki >The t

Re: [computer-go] New scalability study : show uncertainty ?

Don Dailey: <[EMAIL PROTECTED]>: > >> I wonder if fatman trend near 13 is an artefact or if the curve shows it >> has reached some limit in scalabitly. >> >It's rather odd. I'm checking the log file and then I will check the >source code to see if I have some artificial limits in there. Why

Re: [computer-go] Is MC-UCT really scalable against humans?

Petri Pitkanen: <[EMAIL PROTECTED]>: >2008/1/22, Alain Baeckeroot <[EMAIL PROTECTED]>: >> This is not a bug, its a feature of MC program. >> It seems you really know very little about their logic and strenght. >> Try on 9X9 and you will see they are very strong at tactics. >I know their logic. Just

Re: [computer-go] 19x19 cgos ranking page

Have you selected the room with bot's name as a member? -Hideki Olivier Teytaud: <[EMAIL PROTECTED]>: >> The crosstables are back, but the sgf archives ar not. > >Sorry, many troubles since the maintenance of the website... i'm >on that. >___ >computer-

Re: [computer-go] New scalability study : show uncertainty ?

Hi Jacques, Jacques Basaldúa: <[EMAIL PROTECTED]>: >Hideki Kato wrote: > >>> It's rather odd. I'm checking the log file and then I will check the >>> source code to see if I have some artificial limits in there. > > >> Why odd? It all depends

[computer-go] Re: Scalbility study: low end

Heikki, The numbers of games are about 200 and their ratings' standard deviations (right of Elo) are 70 to 100, right now. To get 95% of reliability, you have to double them. Don't you think it's too early to conclude any? -Hideki Heikki Levanto: <[EMAIL PROTECTED]>: >Everyone is looking at

Re: [computer-go] Re: Scalbility study: low end

t always be the stronger players. >The probability of one of them playing against an opponent in the lower >half is low. Hmm, I don't understand what you want to say... Probably you wrote to Heikki, or else? -Hideki >- Don > > >Hideki Kato wrote: >> Heikk

Re: [computer-go] Re: Scalbility study: low end

Oh, I intended to say that this is 68% of confidence interval and if you want 95% then ... Thank you for pointed out. -Hideki >s. > >- Original Message >From: Hideki Kato <[EMAIL PROTECTED]> >To: computer-go >Sent: Thursday, January 24, 2008 8:34:42 AM >S

Re: [computer-go] 19x19 Study - prior in bayeselo, and KGS study

Don Dailey: <[EMAIL PROTECTED]>: >> About Don's arguments on self testing: >> >> I would agree at 100% if it wasn't for the known limitations: >> Nakade, not filling own eyes, etc. Because the program is blind >> to them it is blind in both senses: it does not consider those >> moves when defendin

[computer-go] Re: handtalk at 9x9? (was 19x19 Study - prior...)

Darren Cook: <[EMAIL PROTECTED]>: >> See the handtalk's winning rates on cgos 9x9 >> (http://cgos.boardspace.net/9x9/cross/handtalk.html). >> He won agains MoGo at 60% but his rating is about 200 ELO behind >> it. This happened probably because he know MoGo's weakpoint, >> misunderstanding of L

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

Hi Rémi and all, It's not final version of his thesis, rather it has some (or a lot of :) errors. Please wait for the final version. -Hideki Rémi Coulom: <[EMAIL PROTECTED]>: >Hi, > >I found the Master Thesis of Nobuo Araki is available online: >http://ark.qp.land.to/main.pdf > >Abstract: >Rece

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?

800 but now 1739 and 1723 respectively. My internet connection was unstable a few days recently and they (including mogo-pr-1core) lost some games by Time but I believe it's not the cause. We have to watch some more days or weeks anyway, I think. -Hideki >- Don > > >Hideki Ka

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

Don Dailey: <[EMAIL PROTECTED]>: >Rémi, > >After sending this last message to the list I thought of a couple of things. >Just a few >weeks ago I lowered the default rating about 400 ELO.The default rating is >the initial >rating you receive by default. Although I don't know your idea be

Re: [computer-go] More UCT / Monte-Carlo questions

My program ggmc has been improved about 300 ELO by RAVE. -Hideki Gunnar Farnebäck: <[EMAIL PROTECTED]>: >David Fotland wrote: > > Can you elaborate on what is in a node, and what you mean by expand? I > > assume you have simple node, where each node represents a position and > > the single move

Re: [computer-go] More UCT / Monte-Carlo questions

A playout just returs score and moves with colors in my implementation. -Hideki David Fotland: <[EMAIL PROTECTED]>: >Helps a little, but I'm still unclear on how a new node is handled. > > > >Do you have lightweight nodes (that only contain info on one positions, with >pointers to children and

Re: [computer-go] More UCT / Monte-Carlo questions (Effect of rave)

You are right. I don't do progressive widening. -Hideki Gian-Carlo Pascutto: <[EMAIL PROTECTED]>: >> I also implemented RAVE in Mango. There was a few points of improvements >> (around 60 Elo points with gnugo as reference), but as much as in the >> paper of Gelly and Silver :( (around 250 Elo p

Re: [computer-go] More UCT / Monte-Carlo questions (Effect of rave)

I found some data. GGMC Go v2r6, against GNU Go 3.7.10 level 10, 9x9, komi 7.5, 3000 playouts/move, 2000 games match: Without RAVE: winning rate was 23.1 +- 0.9% (-209 +- 9 ELO) With RAVE: winning rate was 65.3 +- 1.1% (+110 +- 8 ELO) Though this includes some other improvements, most co

Re: [computer-go] More UCT / Monte-Carlo questions (Effect of rave)

Gian-Carlo Pascutto: <[EMAIL PROTECTED]>: >Hideki Kato wrote: > >> 4) Before back-propagating the value of each playout, I setup a color >> table for all intersections of the board for speed-up, in fact >> (initialized with EMPTY). That is, fill the board (table

Re: [computer-go] More UCT / Monte-Carlo questions (Effect of rave)

se anything like FPU or >progressive widening, or did you use Levente's original design which >always selects unvisited moves first? > >Regards, >Erik > > >On Wed, Feb 6, 2008 at 3:42 PM, Hideki Kato <[EMAIL PROTECTED]> wrote: >> I found some data. GGMC

Re: [computer-go] chess/go for handhelds

Though I'm not good at PDA market in Japan, reading Japanese wikipedia, it's seems very small. Sony, which had been making and selling an original Palm, CLIE serie, stopped manifacturing and retired from PDA 2005, for example. No Japanese company sell Palm devices now. I've checked Japanese l

[computer-go] Re: computer-go Digest, Vol 43, Issue 8

Thank you very much, Silver. Interesting report! -Hideki David Silver: <[EMAIL PROTECTED]>: >Hi all, > >On 7-Feb-08, at 1:30 AM, [EMAIL PROTECTED] wrote: > >> Note as well that the current implementation of MoGo (not the one at >> the time of the ICML paper) use a different tradeoff between UCT

Re: [computer-go] Re: computer-go Digest, Vol 43, Issue 8

Olivier Teytaud: <[EMAIL PROTECTED]>: >> That translates to mean that MoGo no longer uses upper confidence >> bounds, and only uses means. It also means that MoGo will _never_ >> explore improbable children (after a few sims) unless the RAVE value >> yields an unusually high estimate for it. Is

[computer-go] Re: MoGo 64 bits, mogo double

Hi Olivier, New versions of MoGo don't put log files, which was very useful to study. Don't you have plan to release such versions put log files? -Hideki Olivier Teytaud: <[EMAIL PROTECTED]>: >For people requesting mogoRelease3 without the bug for long computation >times due to a float instea

Re: [computer-go] Re: MoGo 64 bits, mogo double

lvain Gelly: <[EMAIL PROTECTED]>: >Hi Hideki, > >Isn't possible to just redirect stderr? > >Best, >Sylvain > >2008/2/14, Hideki Kato <[EMAIL PROTECTED]>: >> Hi Olivier, >> >> New versions of MoGo don't put log files, which was very u

[computer-go] Re: Live broadcasting at UEC Cup

Official results of the second day: KCC Igo 1 Katsunari 2 Zen 3 Shikosakugo 4 Many Faces of Go5 Erica 6 Kiseki 7 Galileo 8 Crazy Stone 9 Aya 10 GOGATAKI11 Rock12 Nomitan 13 Kinoa Igo 1

[computer-go] KCC won the 3rd UEC Cup

Official results of the second day: KCC Igo 1 Katsunari 2 Zen 3 Shikosakugo 4 Many Faces of Go5 Erica 6 Kiseki 7 Galileo 8 Crazy Stone 9 Aya 10 GOGATAKI11 Rock12 Nomitan 13 Kinoa Igo 14 boon15 Ker

[computer-go] Re: Live broadcasting at UEC Cup

Woops. Sorry for double posting. Hideki -- g...@nue.ci.i.u-tokyo.ac.jp (Kato) ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/

Re: [computer-go] KCC won the 3rd UEC Cup

Willemien: : >What happened exactly? > >a superko violation which was legal under Japanese rules ? Yes. Jpanese rules inhibit just a simple ko. If a move is not a ko but a superko move, that move is legal under Japanese rules. >It sounds like a contradiction. >(if it is legal it is no violati

Re: [computer-go] KCC won the 3rd UEC Cup

Nick Wedd: <5earkjc29mflf...@maproom.demon.co.uk>: >Many thanks to Hideki Kato for providing the results of the UEC Cup. For >those who cannot read Japanese, this is invaluable. > >I wonder if anyone knows what happened in the GPW Cup, played in Hakone >two weeks earlier?

Re: [computer-go] KCC won the 3rd UEC Cup

Darren Cook: <4b1af9bd.3020...@dcook.org>: >> Rank NameAuthor Score* >> ... >> 11 Katsunari Shinich Sei 2 >> >> Katsunari used alpha-beta search and the others used MCTS. > >Katsunari came second at the UEC cup, but last at GPW Cup.

[computer-go] English results available (Re: KCC won the 3rd UEC Cup)

Official English page: http://jsb.cs.uec.ac.jp/~igo/eng/index.html 1st day results: http://jsb.cs.uec.ac.jp/~igo/eng/result.html 2nd day results: http://jsb.cs.uec.ac.jp/~igo/eng/result2.html In addition, the game records of two extra matches, Crazy Stone vs Zen and Many Faces of Go vs Aya, can b

[computer-go] Re: Congratulations to Zengg!

Nick Wedd: : >Congratulations to Zengg, winner of Sunday's KGS bot tournament. > >My report is at http://www.weddslist.com/kgs/past/54/index.html Thank you Nick. The tournament was quite interesting and exciting. >Zengg9 >Zengg, platform unspecified but probably a cluster Zengg9 run on a (min

<    1   2   3   4   5   >