Peter Drake | 26 Feb 21:45 2015

Debugging Orego/KGS: "Unknown message type -105"

I've finally gotten around to trying to address the issue that Orego faced in the December tournament. As you may recall, every time Orego played black (except the first time), it immediately passed.

Looking at the kgsGTP log, I see some strange things. At the beginning of every game, this happens:


FINEST: Command queued for sending to engine: time_settings 540 30 10

Dec 07, 2014 8:39:00 AM com.gokgs.client.gtp.a l

WARNING: Opponent has left game. Will give them 5 minutes to return.

Unknown message type -105 for channel org.igoweb.igoweb.client.gtp.c <at> cd3509c

Dec 07, 2014 8:39:00 AM com.gokgs.client.gtp.GtpClient d

FINEST: Got successful response to command "boardsize 13": =

Dec 07, 2014 8:39:00 AM com.gokgs.client.gtp.GtpClient d


Does anyone know what this means? Why does the opponent leave? What is the "unknown message type -105"?


--
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Michael Alford | 25 Feb 00:26 2015

Go AI

This link appeared in today's AGA E-journal. It mentions MoGo, Zen, and 
Crazy Stone.

Michael

-------

http://en.wikipedia.org/wiki/Pale_Blue_Dot

_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Nick Wedd | 23 Feb 19:31 2015
Picon

Spring SLOW KGS bot tournament, 19x19

The spring SLOW KGS bot tournament will start next Sunday, March 1st, starting at 22:00 UTC, and ending on Wednesday by 14:00 UTC.  It will use
19x19 boards, with time limits of 235 minutes each plus very fast
Canadian overtime, and komi of 7.5.  There are details at http://www.gokgs.com/tournInfo.jsp?id=947.

Please register by emailing me, with the words "KGS Tournament
Registration" in the email title, at maproom <at> gmail.com .

Nick
--
Nick Wedd      maproom <at> gmail.com
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Michael Alford | 17 Feb 21:26 2015

Numenta

I thought some of you might be interested in this:

  http://numenta.com/#hero

Here's a short teaser :)

https://www.youtube.com/watch?v=RojcnwnEzSQ

Michael

-------

http://en.wikipedia.org/wiki/Pale_Blue_Dot

_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Nick Wedd | 17 Feb 00:01 2015
Picon

Congratulations to Zen!

Congratulations to Zen19S, winner of yesterday's KGS bot tournament!

As usual, I hope you will send me your comments and corrections.

Nick
--
Nick Wedd      maproom <at> gmail.com
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Detlef Schmicker | 8 Feb 11:22 2015
Picon

CNN for winrate and territory

Hi,

I am working on a CNN for winrate and territory:

approach:
 - input 2 layers for b and w stones
 - 1. output: 1 layer territory (0.0 for owned by white, 1.0 for owned by black (because I missed TANH in the first place I used SIGMOID))
 - 2. output: label for -60 to +60 territory leading by black
the loss of both outputs is trained

the idea is, that this way I do not have to put komi into input and make the winrate from the statistics of the trained label:

e.g. komi 6.5: I sum the probabilites from +7 to +60 and get something like a winrate

I trained with 800000 positions with territory information through 500 playouts from oakfoam, which I symmetrized by the 8  transformation leading to >6000000 positions. (It is expensive to produce the positions due to the playouts....)

The layers are the same as the large network from Christopher Clark, Amos Storkey : http://arxiv.org/abs/1412.3409


I get reasonable territory predictions from this network (compared to 500 playouts of oakfoam), the winrates seems to be overestimated. But anyway, it looks as it is worth to do some more work on it.

The idea is, I can do the equivalent of lets say 1000 playouts with a call to the CNN for the cost of 2 playouts some time...


Now I try to do a soft turnover from conventional playouts to CNN predicted winrates within the framework of MC.

I do have some ideas, but I am not happy with them.

Maybe you have better ones :)


Thanks a lot

Detlef

_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Wolfgang Reher | 31 Jan 22:03 2015
Picon
Picon

perhaps bug, HiraBot2 on KGS today

Hi

Look at the last move on KGS in the game

Firzen[3d] - HiraBot2[1d] now about an hour ago.
http://www.gokgs.com/gameArchives.jsp?user=firzen

Is there a bug in the program? 

Have fun
Wolfgang
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Nick Wedd | 28 Jan 11:16 2015
Picon

February KGS bot tournament: 9x9

The February KGS bot tournament will be held on Sunday, February
15th, starting at 16:00 UTC and ending at 22:40 UTC.  It will use
9x9 boards, with time limits of 9 minutes each plus very fast
Canadian overtime, and komi of 7.  Note that the integer komi makes
jigo a possible result.  There are details at
http://www.gokgs.com/tournInfo.jsp?id=944 .

Please register by emailing me, with the words "KGS Tournament
Registration" in the email title, at maproom <at> gmail.com .

Nick
--

-- 
Nick Wedd
nick <at> maproom.co.uk
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Darren Cook | 23 Dec 19:05 2014

Fwd: Announcement Call for Papers ACG 2015 -- deadline 1 March 2015

(I didn't see it, but my apologies if someone already posted this.)

-------- Forwarded Message --------
Subject: Announcement Call for Papers ACG 2015 -- deadline 1 March 2015
Date: Tue, 23 Dec 2014 16:40:17 +0100

Dear all,

With great pleasure we announce the 14th International Conference Advances
in Computer Games 2015, to be held early July 2015, at the University in
Leiden, the Netherlands. (Exact date in early July to be confirmed shortly.)

Papers to the conference will undergo a full peer review process, and
Proceedings are expected to be published in the Springer LNCS Lecture Notes
of Computer Science series.

The ACG2015 conference will be organized, as usual, as part of the ICGA
events, the World Computer Chess Championships and the Computer Olympiad.

Important dates:

Paper submission deadline: 1 March 2015
Notification of acceptance: 25 March 2015
Camera ready papers due: 1 May 2015

Conference website: http://acg2015.wordpress.com
Submissions website: https://www.conftool.net/acg2015  (to be operational
shortly)

Please find attached the Call for Papers including the Program Committee
and further details.

Looking forward to welcoming you in Leiden,
Aske Plaat
Jaap van den Herik
Walter Kosters

Leiden University
Aske

Aske Plaat  -  +31.6.46467007  -  aske.plaat <at> gmail.com  -  http://plaat.nl

_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Andries E. Brouwer | 27 Dec 01:46 2014
Picon
Picon

recognizing games

Erik van der Werf write on 2014-12-15:

> Also, if you're not careful, it is quite easy to get
> duplicate games in your dataset (I've had cases where
> one game was annotated in chinese, and the other (duplicate) in
> English, or where the board was simply rotated). My solution
> around this was to always test on games from the most recent
> pro-tournaments, for which I was certain they could not yet be
> in the training database.

It is quite easy to avoid duplicates using a signature.
For full games, where one only wants to defend against
reflection/rotation, use the minimum of the eight md5sums
of the sequences of moves obtained by rotating and/or reflecting
the board. For possibly truncated games, use the same idea with
as basis a Dyer-type signature on six or eight moves.
Software like sgfinfo computes such signatures.

Andries
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Takeshi ITO | 27 Jan 13:21 2015

Call for participation: The 8th UEC-cup Computer Go Tournament


Dear All,

   We are pleased to announce the 8th UEC-cup Computer Go Tournament as 
follow.
   Registration is now open!
   We are looking forward to your participating.

Best regards,

--------------------------------------------------------------------
The 8th UEC cup Computer Go Tournament

Competition Dates
   March 15-15, 2015

Rule
   Japanese rules on 19x19 board.
   Time control of 30 minutes without Byoyomi

Competition Venue
   Building W-9 3F AV hall(campus map:68)
   The University of Electro-Communications
   1-5-1 Chofugaoka, Chofu-shi, Tokyo 182-8585 Japan.

Registration Deadline
   February 28, 2015

Prizes
   Top 8 programs will be awarded.
   In addition, each of the top three programs will be awarded
  an ornament and money presented in the following table according to 
its rank.

-----------------------
   Rank  Money(JPY)
    1     300,000
    2     100,000
    3      50,000
-----------------------

Organizers
   The University of Electro-Communications
   Cognitive Science and Entertainment (E&C) Research Station

Supporter
    IGO & SHOGI CHANNEL INC.

Sponsors
   Computer Go Forum

Under the auspices of
   The Nihon Ki-in
   The Japanese Society for Artificial Intelligence

Web:http://jsb.cs.uec.ac.jp/~igo/eng/

----------------------------------
  Takeshi Ito
  Chairperson of this tournament

_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Gmane