Nick Wedd | 29 Aug 16:37 2015
Picon

Autumn SLOW KGS bot tournament, 19x19

The autumn SLOW KGS bot tournament will start on Sunday September 5th
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

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
Denis Blumstein | 28 Aug 23:00 2015
Picon

[ANN] yet another go engine : michi-c release 1.4 on GitHub

Hi,

michi-c is a port in C of the michi program by Petr Baudis with the same 
goals (see https://gitub.com/pasky/michi).

It has many of the extensions that Petr has hoped:
- early passing,
- graphics in gogui,
- parameters modifications by gtp commands,
- speed improvement by tracking liberties and blocks,
- preliminary time management and dynamic komi
- read simple SGF files
- small user manual

Currently (version 1.4), it runs exactly the same algorithms as the 
michi python version.

The michi goal for brevity has been relaxed in favor of speed and 
functionalities.

Michi-c is relatively fast even if there is still much room for 
improvements. It runs 3200 playouts/s from an empty 19x19 board on an 
i7-4790K (single threaded and using large patterns). With this setting, 
it plays about even with gnugo on 19x19 (winrate 57 % +/- 2.5% measured 
on 400 games) at an average speed of 400 seconds per game (about 3.3 
sec/move).

The development is done on Linux but the goal is to keep the code portable.
Michi-c comes with everything included. The only requirements are :
- a C compiler with the standard C library to build the gtp engine,
- gogui (http://gogui.sourceforge.net) to use the engine confortably if 
gogui is supported on your system.

The code for the MCTS tree search and the playout policy is about 1000 
lines of C (20 % of the total).

Michi-c can be downloaded at https://github.com/db3108/michi-c2. It is 
distributed under the MIT license.

Thanks to Horace Ho, Andreas Pearson, Eric Steinmetz and J.Kartz who 
have provided feedback and/or corrections about portability issues of 
earlier versions with IOS (iphone 6), Windows 32 bits system with 
Microsoft Visual Studio and MAC OS X.

And of course, many thanks to Petr Baudis for having published the 
michi.py code and setting up the goals for this project.

Denis
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
djhbrown . | 28 Aug 14:34 2015
Picon

Group Strength (Part 1)

_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Daily Pro Go | 27 Aug 03:28 2015
Picon

Javascript go programs

Short version: Is anyone aware of any attempts at writing a program to play go in javascript?

Long version: I am a longtime (4-5dan) go player and hobbiest programmer and wanted to try exploring some of the challenges around writing a go playing program. However, javascript is by far my strongest coding language and I didn't think it would be wise to dive into a less familiar language at the same time I'm learning about lots of other new things like MCTS. I know there's a performance penalty for a language like js, but since my first attempts will probably be quite crude anyway, this seems like something I can defer until later. With all that said, do you know of any other js go playing programs that could provide some good initial stubs/ideas as I try to dive in? I'd be particularly interested if anyone has already made a link between gogui and a javascript program.

Thanks!
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
djhbrown . | 25 Aug 03:59 2015
Picon

Re: how do I start building a Computer Go AI?

your question contains its answer:

to build a computer Go AI, you need to learn
1. computer
2. Go
3.  AI

you have made good progress on 2; now you need to learn 1 and 3.

one way to do this is to take a college course, as you propose to do.
it is unlikely you can put 1, 2 and 3 together before you enrol,
unless you are like Mozart.

i would recommend reading the links in this to get a taste of what the
mountain you want to climb looks like:
http://www.citeulike.org/group/5884/library/order/year,desc,

--

-- 
http://sites.google.com/site/djhbrown2/home
https://www.youtube.com/user/djhbrown
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Cai Gengyang | 24 Aug 10:24 2015
Picon

Re: Computer-go Digest, Vol 67, Issue 14

Hi,

Is there a download link for the Michi --- Minimalistic Go MCTS Engine? I would like to use it to learn how to build a Go engine ...

Gengyang

On Sat, Aug 22, 2015 at 8:00 PM, <computer-go-request <at> computer-go.org> wrote:
Send Computer-go mailing list submissions to
        computer-go <at> computer-go.org

To subscribe or unsubscribe via the World Wide Web, visit
        http://computer-go.org/mailman/listinfo/computer-go
or, via email, send a message with subject or body 'help' to
        computer-go-request <at> computer-go.org

You can reach the person managing the list at
        computer-go-owner <at> computer-go.org

When replying, please edit your Subject line so it is more specific
than "Re: Contents of Computer-go digest..."


Today's Topics:

   1. Re: Building A Computer Go AI (robertfinkng555 <at> o2.co.uk)
   2. Re: Building A Computer Go AI (Andy)
   3. Re: Building A Computer Go AI (David Doshay)


----------------------------------------------------------------------

Message: 1
Date: Fri, 21 Aug 2015 13:06:16 +0100
From: "robertfinkng555 <at> o2.co.uk" <robertfinkng555 <at> o2.co.uk>
To: computer-go <at> computer-go.org
Subject: Re: [Computer-go] Building A Computer Go AI
Message-ID: <55D71438.2080107 <at> o2.co.uk>
Content-Type: text/plain; charset=utf-8; format=flowed

Hi,

Good news. There are a variety of open source projects out there,
including both complete programs (Fuego, Pachi) as well as libraries to
build your own Go engine (libEgo). There are also a wealth of papers
explaining the theory behind the top algorithms. Try googling "AMAF
algorithm" or "RAVE algorithm" or "MCTS algorithm" or "TD Search
algorithm" as a starting point. There is a nice Thesis on Pachi too
google "Pachi Thesis".

I hope this helps :-)

Regards

Raffles

On 21-Aug-15 8:48, CaiGengYang wrote:
> Hello …
>
>
> I am a 3d~~5d go player from Singapore.
>
> Keen to learn how to build a powerful Computer Go AI to compete in the Computer Go Tournament and also for admissions to a Computer Science college program.
>
> Have very little programming experience except following some code examples on CodeAcademy … how do I start building a Computer Go AI ?
>
>
> Gengyang
> _______________________________________________
> Computer-go mailing list
> Computer-go <at> computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
> -----
> No virus found in this message.
> Checked by AVG - www.avg.com
> Version: 2015.0.6125 / Virus Database: 4392/10476 - Release Date: 08/21/15



------------------------------

Message: 2
Date: Fri, 21 Aug 2015 09:22:45 -0500
From: Andy <andy.olsen.tx <at> gmail.com>
To: r <at> ffles.com, computer-go <computer-go <at> computer-go.org>
Subject: Re: [Computer-go] Building A Computer Go AI
Message-ID:
        <CAAtbd5DfpxmsnBHQH1V4m7s5-L0XzreUd_kunr8i+WLZYekuCQ <at> mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Here is a simple working implementation.
https://github.com/pasky/michi

>From the beginning of the readme:

Michi --- Minimalistic Go MCTS Engine

Michi aims to be a minimalistic but full-fledged Computer Go program based
on state-of-art methods (Monte Carlo Tree Search) and written in Python.
Our goal is to make it easier for new people to enter the domain of
Computer Go, peek under the hood of a "real" playing engine and be able to
learn by hassle-free experiments - with the algorithms, add heuristics, etc.

The algorithm code size is 540 lines of code (without user interface,
tables and empty lines / comments). Currently, it can often win against
GNUGo on 9×9 on an old i3 notebook, be about even with GNUGo on 15×15 on a
modern higher end computer and about two stones weaker on 19×19 (spending
no more than 30s per move).

This is not meant to be a competitive engine; simplicity and clear code is
preferred over optimization (after all, it's in Python!). But compared to
other minimalistic engines, this one should be able to beat beginner
intermediate human players, and I believe that a *fast* implementation of
exactly the same heuristics would be around 4k KGS or even better.

Michi is distributed under the MIT licence. Now go forth, hack and peruse!





On Fri, Aug 21, 2015 at 7:06 AM, robertfinkng555 <at> o2.co.uk <
robertfinkng555 <at> o2.co.uk> wrote:

> Hi,
>
> Good news. There are a variety of open source projects out there,
> including both complete programs (Fuego, Pachi) as well as libraries to
> build your own Go engine (libEgo). There are also a wealth of papers
> explaining the theory behind the top algorithms. Try googling "AMAF
> algorithm" or "RAVE algorithm" or "MCTS algorithm" or "TD Search algorithm"
> as a starting point. There is a nice Thesis on Pachi too google "Pachi
> Thesis".
>
> I hope this helps :-)
>
> Regards
>
> Raffles
>
>
> On 21-Aug-15 8:48, CaiGengYang wrote:
>
>> Hello …
>>
>>
>> I am a 3d~~5d go player from Singapore.
>>
>> Keen to learn how to build a powerful Computer Go AI to compete in the
>> Computer Go Tournament and also for admissions to a Computer Science
>> college program.
>>
>> Have very little programming experience except following some code
>> examples on CodeAcademy … how do I start building a Computer Go AI ?
>>
>>
>> Gengyang
>> _______________________________________________
>> Computer-go mailing list
>> Computer-go <at> computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>> -----
>> No virus found in this message.
>> Checked by AVG - www.avg.com
>> Version: 2015.0.6125 / Virus Database: 4392/10476 - Release Date: 08/21/15
>>
>
> _______________________________________________
> Computer-go mailing list
> Computer-go <at> computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20150821/9c8b930e/attachment-0001.html>

------------------------------

Message: 3
Date: Fri, 21 Aug 2015 10:25:35 -0700
From: David Doshay <ddoshay <at> mac.com>
To: computer-go <at> computer-go.org
Subject: Re: [Computer-go] Building A Computer Go AI
Message-ID: <0FC33771-37F2-4EA9-8A56-89A7A5D23D7B <at> mac.com>
Content-Type: text/plain; charset=utf-8

It depends very much upon what you mean by a “powerful Computer AI.” If you mean a modern Go playing program then all the advice about MCTS is good. If you mean an AI that depends more upon traditional Go knowledge, then the MCTS systems will not interest you, even though the mature MCTS bots are now much stronger than the traditional systems. If you are interested in the knowledge/pattern based systems then take a look at GNU Go. It is large and there will be a learning curve, but it is where I started when I built SlugGo, which was strong enough to win the KGS tournaments it entered until it was surpassed by the MCTS programs.

Given your limited programming experience, I suggest Michi because Python is easy to read. While Libego is very fast, some of the C++ constructs can take a while to figure out, so modifying or adding to the code is harder.

Good luck!


Cheers,
David G Doshay

ddoshay <at> mac.com





> On 21, Aug 2015, at 12:48 AM, CaiGengYang <gengyangcai <at> gmail.com> wrote:
>
> Hello …
>
>
> I am a 3d~~5d go player from Singapore.
>
> Keen to learn how to build a powerful Computer Go AI to compete in the Computer Go Tournament and also for admissions to a Computer Science college program.
>
> Have very little programming experience except following some code examples on CodeAcademy … how do I start building a Computer Go AI ?
>
>
> Gengyang
> _______________________________________________
> Computer-go mailing list
> Computer-go <at> computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go



------------------------------

Subject: Digest Footer

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

------------------------------

End of Computer-go Digest, Vol 67, Issue 14
*******************************************

_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
CaiGengYang | 21 Aug 09:48 2015
Picon

Building A Computer Go AI

Hello …

I am a 3d~~5d go player from Singapore. 

Keen to learn how to build a powerful Computer Go AI to compete in the Computer Go Tournament and also for
admissions to a Computer Science college program.

Have very little programming experience except following some code examples on CodeAcademy … how do I
start building a Computer Go AI ?

Gengyang
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
"Ingo Althöfer" | 11 Aug 16:54 2015
Picon
Picon

Computer-aided Go on High-dan Level

Hello,
during the European Go Congress 2015 (two weeks ago in
Liberec) there was also a conference on "Science and Go".
The proceedings are online, in pdf:
https://www.sharelatex.com/github/repos/pasky/iggsc2015proc/builds/190ba3e8c196560223fda9855ed0d54312e8ca69/raw/output.pdf
including the paper
"Computer-aided Go on high-dan level" by Manja Marz, Stefan Kaitschick and me.

There is also a Youtube video of the conference, although 
sound (partly double echo; but only for a few minutes) is 
not optimal in it.

https://www.youtube.com/watch?v=8AZsWAV2org
Our presentation starts at 6min:45sec and lasts until
31min:30sec (including discussion).

Feedback, either by private email or here in the group is welcome.

Ingo.
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Nick Wedd | 10 Aug 19:29 2015
Picon

Congratulations to Zen!

Congratulations to Zen19X,  winner of yesterday's 13x13 KGS bot tournament, with 17 wins from 18 games!

As usual I welcome 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
djhbrown . | 3 Aug 03:33 2015
Picon

Mental Imagery in Go - playlist

Thanks for the replies to my first message; i looked at the links you supplied and comment on them later in this email.

I noticed that Google does not show you the playlist when you look at episode 1 of the series (of currently 3 videos), so you may have missed the second two episodes which are more significant than the first.  Here is a link to the playlist:

https://www.youtube.com/playlist?list=PL4y5WtsvtduqNW0AKlSsOdea3Hl1X_v-S

episode 2 introduces mental images and episode 3 is a conversation between Hajin Lee and me about her thoughts on a couple of moves early in one of her games.  It includes my first attempt at "picturing" her thoughts, both as symbolic information structures and as paint overlays on the game board.

My hope is that the former might one day become the basis of symbolic generic heuristic rules that could be used to generate and evaluate move candidates and the latter could evolve into useful instructional materials for people learning the game - so that they can, so to speak, "look through the eyes" of an expert like Hajin.

To these ends, i need the assistance of people with better skills than me at (a) drawing pictures, (b) software and (c) Go.  I think that programming is like gymnastics - best done by the young, with their abundance of enthusiasm and energy.  I enjoyed programming 50 years ago, but i'm too old in the tooth now to burn midnight oil.

Now to your replies:

Folkert: "Stop" is a good start but as you already know, there's a long way to go yet :)

Steven:  I expect there is a future for CNN's in recognising static images, but my gut feel is that a position in a Go game is more like one frame of a movie; as such, it requires a technology that can interpret dynamic images - maybe work being done in automatous car driving can contribute something useful to Go playing?  Nevertheless, I was surprised by the many humanlike moves of DCNNigo on KGS (until it revealed its brittleness).  To be sure, drawing upon the moves of experts is one way of gaining expertise, but my feeling is that one should try to abstract the position - to generalise from the examples - so that general knowledge can be formed and applied to novel situations.  It may be that a CNN arguably does do some kind of generalisation - but can it, for example, characterise something as basic as "the waist of a keima"?

Ingo:  Tanja may be the kind of artist who could produce nice drawings of Hajin's mental images, perhaps based on my own crude sketches?  It would be unpaid work though...  I liked Fuego's and Jonathan's territory pictures, which reminded me of Zobrist's early work on computing influence.  [Albert Zobrist (1969). A Model of Visual Organisation for the Game of Go. Proceedings of the Spring Joint Computer Conference, Vol. 34, pp. 103-112.] However, whereas being able to picture influence and territory is one of my objectives, i want to try to picture the richness of what Hajin (aka Haylee) sees rather than the result of a primitive computation.  For example, at 10:24 in episode 3, she points out that when black is on J4 instead of K4, there is an opening in black's lower side for white to invade.  This tiny gap makes all the difference to the dynamic meaning of the position a few moves prior (ie whether it is sensible for white to approach Q3 at Q5). 

One of the major influences on my own thinking about Go programming is the seminal work "Thought and Choice in Chess" by Adriaan de Groot  which i reckon is well worth a read by anyone interested in programming Go
https://books.google.com.au/books?id=b2G1CRfNqFYC&pg=PA99

---
_______________________________________________
Computer-go mailing list
Computer-go <at> computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
Aguido Davis | 3 Aug 02:22 2015
Picon

Rating systems in thin/sparsely connected populations of players

Good morning.

We're looking at replacing the Australian national ranking system, and the question has come up: how many players and how many recent games/player are needed for ELO to generate good strength ratings?

(Questions begged: what does a "good" set of ratings even mean? does it matter if the play graph (edges = games, vertices = players) is well-connected or quite cliquey? is ELO the last word in rating algorithms? do humans behave differently from bots when they know they're being rated?)

Does anybody know of a good academic paper, or ideally, someone's thesis? 

My apologies if this is off-topic, but it's an interesting computation related to go...

Cheers,

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

Gmane