gtp

gtp@lists.lysator.liu.se

164 discussions

qGo client
by pstrempel＠t-online.de 06 May '02

06 May '02

Hello, qGo, a relatively new SGF editor, is now able to act as an interface to play games with gnugo using GTP. The project is still in an early stage and the release is a preview. qGo allows you to: * play against gnugo (human vs computer) * undo moves * control and debug gnugo via GTP console * score games using qGos own scoring * guess the score using gnugo I am sure it is anything but bugfree, but I managed to play a couple of games against gnugo without big problems. Handicap is currently not yet possible. qGo is available at http://qgo.sourceforge.net/java/ Please note there is also a Qt version, this one does not have the GTP features (maybe somewhen in the future). I have not seen GTP before, but I must say, it is very smooth and easy to use as programmer. I got the basic engine for playing done in a night. Don't want to think how long that had taken with GMP. Great work! Peter

1 0

NNGS-devel
by A van Kessel 04 Mar '02

04 Mar '02

Daniel Bump wrote: > Nils Lohner and Adriaan van Kessel undertook a project > of rewritting the NNGS server code. They had some idea > of converting the protocols to XML. But they didn't > get very far with the protocol revision. Also, as far > as I know no server uses their code. I am still working on the code, but at the moment at a very low pace. I have *never* considered XML. It would solve no problem. My first objective is still to get the NNGS-sources into a usable shape. A lot of bloat has been removed already. There has been an attempt to remerge with a chinese nngs-clone (they had translated all the text-strings they could find ...), and that has resulted in a (clumsy, but stable) variable language -feature. I have looked at gtp as a candidate protocol. At the moment, gtp will *not* work. currently, GTP has no notion of a game, it is just a Q&A like protocol for controlling the knobs and switches on an engine. The real problem here IMO is "installed base". We cannot change the protocol without breaking clients. And we don't want to loose clients. Eventually, even the changes/additions to the IGS-protocol that were introduced by NNGS (embrace and extend ???) should be removed or become optional. At the moment the code is probably not used in any production server, I agree. I hope/expect, however that at one time nngs.cosmic.org will switch to the newer code base, because the old code is becoming more and more unmaintainable. Nils tranformed the codebase to autoconf/automake, and I intend to replace all hard-coded pathnames/filenames by a configuration- file mechanism. This kind of change should simplify first-time installations. Maybe it could help administration of existing installations, too. Increasing use of NNGS can be expected for testing purposes: creation/testing of client programs, local tournaments between computer programs, etc, Any hints/tips/thoughts are wellcome ... AvK

1 0

Go Server Protocols
by Hellwig Geisse 27 Feb '02

27 Feb '02

Hi, I know that this is a bit off-topic here, but I guess that people reading this list could also be interested in the following question: Where are - if at all - go server protocols discussed/specified? Any pointers are welcome. Thanks, Hellwig

3 2

Re: [gnugo-devel] Patch: GTP:worm_origins
by Daniel Bump 27 Jan '02

27 Jan '02

In http://mail.gnu.org/pipermail/gnugo-devel/2002-January/001187.html http://mail.gnu.org/pipermail/gnugo-devel/2002-January/001190.html http://mail.gnu.org/pipermail/gnugo-devel/2002-January/001196.html Heikki wrote > Of course, if you don't want to use the patch, it is all right - I just keep > it in my private fork then. I would assume the first patch is OK but the second one I'd wait for Gunnar's comment on because it modifies the behavior of one of the 14 standard gtp commands. It may be a good modification of that command in which case perhaps the specification should be revised.

1 0

gothic 0.6.5
by Tanguy Urvoy 15 Jan '02

15 Jan '02

Hi, the last version of gothic is available at http://www.irisa.fr/prive/Tanguy.Urvoy/gnugo/gothic-0.6.5.tgz This version is still alpha but promissing: - you can already play against gnugo. - you can send GTP commands during the game via GTP shell. - you can undo moves. - gothic can show you the dragons and their status during the game (red for dead, green for alive, orange for critical). ... For those who do not have Qt 2.3 installed on their computer a screenshot is available here: http://www.irisa.fr/prive/Tanguy.Urvoy/gnugo/screenshot.jpg There are some problems: Gothic is a bit too slow. Because GTP commands are synchrones gothic must wait the answer of the engine before doing anything, we cannot "see the engine at work". Why not consider asynchrone GTP commands ? Please try it and send us comments and bug reports. -- ---------------------------------------------------- Tanguy Urvoy http://www.irisa.fr/prive/Tanguy.Urvoy/ ----------------------------------------------------

4 4

Re: Yet another GTP extension
by William M. Shubert 08 Dec '01

08 Dec '01

I think this would need some changes. This will only support Canadian byo-yomi and non-byo-yomi tournaments. We should make sure that any clock protocol supports other time systems and it should be easy to add new time systems later. So I'd recommend: set_clock <time system> <parameters> I think the following time systems would cover all common Go clocks: * set_clock none * set_clock absolute <time> * set_clock canadian <time> <byoyomi time> <byoyomi stones> * set_clock japanese <time> <byoyomi time> <byoyomi periods> * set_clock ing <time> <byoyomi time> <byoyomi cost> [<byoyomi time 2> <byoyomi cost 2> [...]] That should do it. We could probably even leave Ing out - in my experience, even tournaments run by the Ing foundation don't often use the Ing "pay points for more time" system. On Fri, 2001-12-07 at 03:01, Tanguy Urvoy wrote: Most computer tournaments include a time constraint I suggest 3 new GTP commands: set_clock <main time> <byoyomi time> <byoyomi stones> get_clock_time <color> get_clock_stones <color>

2 2

Yet another GTP extension
by Tanguy Urvoy 06 Dec '01

06 Dec '01

Hello, Most computer tournaments include a time constraint I suggest 3 new GTP commands: set_clock <main time> <byoyomi time> <byoyomi stones> get_clock_time <color> get_clock_stones <color> -- ---------------------------------------------------- Tanguy Urvoy http://www.irisa.fr/prive/Tanguy.Urvoy/ ----------------------------------------------------

1 0

GTP and Gothic
by Tanguy Urvoy 28 Nov '01

28 Nov '01

Hello, I accept your decision not to include a "dump" extension to avoid a break in the protocol. For the same reason, the first version of Gothic will only use GTP 1.0 commands. Gothic will also include a GTP shell for non standard commands like dump board or list_stones :) -- ---------------------------------------------------- Tanguy Urvoy http://www.irisa.fr/prive/Tanguy.Urvoy/ ----------------------------------------------------

1 0

Re: [gnugo-devel] GTP extension for passive GUI
by Daniel Bump 28 Nov '01

28 Nov '01

Tanguy Urvoy has been advocating an extension to the GTP. The place for this discussion is the GTP list, not the GNU Go list. The proposal being discussed is at: http://www.irisa.fr/prive/Tanguy.Urvoy/gnugo/tanguy-3.1.15.1 See also http://mail.gnu.org/pipermail/gnugo-devel/2001-November/000650.html In http://mail.gnu.org/pipermail/gnugo-devel/2001-November/000656.html Tanguy wrote: > I admit that the list representation is good for certain things like > listing the stones of a dragon or giving the list of best moves. > I also admit that everything can be done with list of positions, > but please also consider the other approach. We can do three things: (1) Disallow this change; (2) Allow it but consider it a GNU Go extension; (3) Allow it and make it to be part of the protocol. Gunnar doesn't like this because it is inconsistent with the overall approach of the protocol. Also, Tanguy's reasons don't seem convincing to me. I'll comment on those below. That said, there seems to be no real harm to exercising option (2) above, adding it but considering it a GNU Go extension. However that would mean that the client you write works with GNU Go but not other GTP engines. However is (2) really an option? Other client writers will discover that by making a nonstandard protocol extension they can use GoThic which will create pressure to break the standard leading to a fragmented protocol. I stated that Tanguy's reasons don't seem convincing. > - To keep a humand readable format. > (this is one the GOALS of GTP to be human readable and this is why > people prefer C language to assembly language). We can get an image of the board using the showboard command. It comes over stderr so as not to pollute the stdout channel. It does not show which moves are illegal, and that might be a nice extension. It is not designed for communicating with a client. > - To reduce the traffic in the pipe. This was a goal with the gmp but never with the gtp. > - To use an easy to parse format (no need to use bison nor flex) Both formats are very easy to parse. GNU Go does not use bison or flex to parse the GTP. You are talking about a few lines of C code. > - To use an easy to extend format What extensions do you have in mind? > - To use a color independant representation of legal moves. > ('.' is legal for all, 'x' only for black and 'o' only for white) This point is somewhat valid. Basically the advantage I see to your format is that it makes it harder for the engine to produce inconsistent data. One might imagine a bogus engine returning a list of vertices to the commands list_stones_black, list_stones_white, all_legal_black, all_legal_white which do not represent a valid board. Tanguy's format would make inconsistent data easier to detect. But that doesn't seem an adequate reason to me. Dan

1 0

Reciprocal Links
by Gloria 26 Nov '01

26 Nov '01

1 0

← Newer
1
...
7
8
9
10
11
12
13
...
17
Older →

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

2001

gtp