s.google.com/site/djhbrown2/home
>> >https://www.youtube.com/user/djhbrown
>> >___
>> >Computer-go mailing list
>> >Computer-go@computer-go.org
>> >http://computer-go.org/mailman/listinfo/computer-go
>
+/r+j6IuJboAQtAYcf
> =ZdLw
> -END PGP SIGNATURE-
> ___________
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
--
r-go mailing list
>>> Computer-go@computer-go.org
>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>>
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer
@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
--
=
Olivier Teytaud, olivier.teyt...@inria.fr, TAO, LRI, UMR 8623(CNRS - Univ.
Paris-Sud),
bat 490 Univ. Paris-Sud F-91405 Orsay Cedex France
http://www.slideshare.net/teyt
sign a document with logos in black & white." A. Einstein
Olivier Teytaud, olivier.teyt...@inria.fr, http://www.slideshare.net/teytaud
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
ed for people
working with these tools, even if they don't touch games, and this is
really useful for the world :-)
--
=
"I will never sign a document with logos in black & white." A. E
research :-)
--
=
"I will never sign a document with logos in black & white." A. Einstein
Olivier Teytaud, olivier.teyt...@inria.fr, http://www.slideshare.net/teytaud
___
Computer-go mailing list
Computer-go@computer-go.org
>
>
> I am pretty sure that such an implicit expression exists: it is << the
>> number of etc etc
>>
>
> We do not speak of just the definition of what kind of number to find, but
> of the construction of finding the number (or already of a compression of
> its explicit digits).
It's hard to
your favorite set of rules :-) ).
--
=============
Olivier Teytaud, INRIA TAO Research Fellow ---
http://www.slideshare.net/teytaud
"Please stop quoting me on internet."___ Albert Einstein
___
Computer-go mailing list
Computer-go@c
istence. I don't know the
> details of how DeepMind operates, but I'd imagine the company works
> on multiple things at once. :-)
>
> --
> Petr Baudis
> If you have good ideas, good data and fast computers,
> you can do almost anything. -- Geoffrey Hinton
>
Ok, it's not blitz according to http://senseis.xmp.net/?BlitzGames
(limit at 10s/move for Blitz). But really shorter time settings.
I've seen (as you all) many posts guessing that AlphaGo will lose, but I
find
that hard to know. If Fan Hui had won one game, I would say that AlphaGo is
not ready
that
> you like today?
> Is there a link to such a rule set somewhere?
>
> Thanks,
> -- Mark Goldfain
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
--
In case the question is more on the computational part, you might
use a binary tree, so that you do the selection in time O(log(number of
moves))
instead of O(number of moves). The update is also in logarithmic time for
some probability update rules (to be discussed, depends on how you modify
your
Hello;
we would like to come back to Computer-Go,
starting with the small 9x9 board; is there any such Cgos running somewhere ?
Thanks to people currently running the 13x13.
Or maybe we should run a 9x9 server ourselves if nobody has this in
his/her agenda ?
Best regards,
Olivier
I'm sure many people are curious - MoGo(TW?) doesn't participate much
in computer tournaments nowadays, are you working on some new exciting
things or is the project mostly asleep right now? :-)
Competitions are very boring and time consuming. Other people from the mogo-team
can participate in
Apparently an opening book cannot be used with a stronger or weaker Go
player as-is, but I wonder how useful it would be as a seed?
If we follows the fictitious play algorithm, maybe we should accept
a modification
of the opening book only after comparison with *all* previous versions
of the
This is very interesting, do you have pointers to any papers or
presentations concerning MCTS applications like this in any detail?
If not yet, I'm sure many people on this list will be interested
to hear about any publications in this area too when you finish some
of the applications.
I recommend the paper
http://hal.inria.fr/docs/00/36/97/83/PDF/ouvertures9x9.pdf by the Mogo team,
which describes how to use a grid to compute Mogo's opening book using
coevolution.
I must precise that you often find bad moves in the opponing book.
Doing this grid-based opening-book building
I've found that AMAF gives very little boost with light playouts,
Thanks for this interesting comment.
I would (erroneously) have believed that AMAF gives
better results with non-optimized implementation (e.g. in Havannah with no
expertise Amaf provides huge improvements). In particular, I
• record results for all visited
nodes___
Where do you record the results?
In each node, you keep the statistics of simulations in this node. Many
informations can be useless in each node: rave values (the gellysilver
paper I've emailed to you)
You can see and hear Elwyn Berlekamp delivering a 2006 talk about
Mathematics and Go (culminating in a discussion of coupon go) at:
http://www.youtube.com/view_play_list?p=005B561126D6A51E .
Thanks a lot for pointing out this very interesting video. Seemingly, the
nice historical
://www.computer-go.org/mailman/listinfo/computer-go/
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
--
=
Olivier Teytaud
In your (or Sylvain's?) recent paper, you wrote less than one second
interval was useless. I've observed similar. I'm now evaluating the
performance with 0.2, 0.4, 1 and 4 second intervals for 5 second per
move setting on 19x19 board on 32 nodes of HA8000 cluster.
Yes, one second is fine
Even if the sum-up is done in a logarithmic time (with binary tree
style), the collecting time of all infomation from all nodes is
proportional to the number of nodes if the master node has few
communication ports, isn't it?
No (unless I misunderstood what you mean, sorry in that case!) !
Interesting, surely the order is almost logarithmic. But how long it
takes a packet to pass through a layer. I'm afraid the actual delay
time may increase.
With gigabit ethernet my humble opinion is that you should have no problem.
But, testing what happens if you artificially cancel the
The performance gap is perhaps due to the algorithms. Almost all
cluster versions of current strong programs (MoGo, MFG, Fuego and Zen)
use root parallel while shared memory computers allow us to use thread
parallelism, which gives better performance.
I think you should not have troubles
How to activate patterns?
Why they are not on on default?
They are the default, but they are removed if
they are not in the path when running (it can be seen
on the stderr - the number of patterns read must be 0).
In 19x19 there is a big impact.
(In the release, there's no pattern)
Olivier
/
--
=
Olivier Teytaud (TAO-inria) olivier.teyt...@inria.fr
Tel (33)169154231 / Fax (33)169156586
Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS - Universite Paris-Sud),
bat 490 Universite Paris-Sud 91405 Orsay Cedex France
(one of the 56.5 % of french
http://computer-go.org/pipermail/computer-go/2009-June/018773.html
As I've often said something related to that (e.g. in
http://hal.inria.fr/inria-00369786/fr/ ) I'd like to be more precise. What
follows is for binary deterministic games, and I precise at the beginning
that this is not
/%7Edrake/
On Nov 9, 2009, at 10:15 AM, Olivier Teytaud wrote:
Hi; I'd like to answer your post but I must admit I've
not clearly understood.
My PDF file is essentially a mathematical analysis, proving that we can
have consistency with some rules, without having infinitely many visits
/listinfo/computer-go/
--
=
Olivier Teytaud (TAO-inria) olivier.teyt...@inria.fr
Tel (33)169154231 / Fax (33)169156586
Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS - Universite Paris-Sud),
bat 490 Universite Paris-Sud 91405 Orsay Cedex
... I'll try
to have some translations here with our chinese students.
Best regards,
Olivier
--
=
Olivier Teytaud (TAO-inria) olivier.teyt...@inria.fr
Tel (33)169154231 / Fax (33)169156586
Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS
Yes, this group does not have a consensus at all on this. On the one
hand we hear that MCTS has reached a dead end and there is no benefit from
extra CPU power, and on the other hand we have these developers hustling
around for the biggest machines they can muster in order to play matches
Just curious, who actually claimed that and what was it based on?
I don't know who claimed it first, and who agreed for it,
but I agree with it :-)
More precisely, I think that increasing time and computational power
makes computers stronger, but not for some particular things like
long-term
But is it shown that the score is well done for these properties to
hold in case of RAVE-guided exploration? Since it massively perpetuates
any kind of MC bias...
This only matters for the fact that we don't visit all the tree. For the
consistency (the fact that
asymptotically we will find
If there are people interested in a ph.D. or a post-doc around Monte-Carlo
Tree Search, candidates are welcome (Monte-Carlo Tree Search, and not
necessarily / not only computer-go).
Excuse me, but what press conference and where to ask?
People interested in a ph.D. or a post doc can
Could you give us at least a general picture of improvements compared to
what was last published as
www.lri.fr/~teytaud/eg.pdfhttp://www.lri.fr/%7Eteytaud/eg.pdf? Is it just
further tuning and small tweaks or are you trying out some exciting new
things? ;-)
There is one important
AIUI, once upon N simulations in a node you take let's say the node with
the lowest value, pick one son of it at random within the tree and start
a simulation?
I'll try to write it clearly (for binary deterministic games, extensions can
be shown but they are too long and out of topic in
Dear all, some comments by my Taiwanese colleagues about the game played by
MoGo against the 9p pro:
1) mogoTW finally ran on the 16*8 system on Oct. 26, 2009.
2) Contributors for which I did not know their real name: Hsien-Der Huang
and Cheng-Wei Chou (sorry for them!)
3) Some comments by the
I forgot the most important thing around this win against a pro:
this press conference was for the starting of a project, and in this project
we have funding for ph.D. or postdocs.
If there are people interested in a ph.D. or a post-doc around Monte-Carlo
Tree Search, candidates are welcome
(Sylvain et al. 2006) describes the use of CFG-based zones in random
simulations to simulate only the local position and tune the score based
on few thousands of simulations of outside of the zone. It doesn't seem
the idea is too practical (especially with RAVE, but there seem to be
more
Dear all,
For information, our Taiwanese partners(**) for a ANR grant have organized
public demonstration games between
MoGoTW (based on MoGo 4.86.Soissons + the TW modifications developped
jointly with our Taiwanese colleagues)
and
C.-H. Chou 9P, top pro player winner
We tested mogo on several Linux clusters, and if MPI
is available everything is fine. If you want the code, I can send you
a .tar.gz and a README on how to make it run. Real time discussion
with gmail-talk or something like that is a good tool also.
My humble opinion on the relevance of
What's your general approach? My understanding from your previous posts
is
that it's something like:
Your understanding is right.
By the way, all the current strong programs are really very similar...
Perhaps Fuego has something different in 19x19 (no big database of patterns
?). I'm not
hi;
I don't know to which extent my terminology is commonly used, but it seems
to be close to the distinction by Dave (but not exactly equal).
For me I use progressive widening when we add moves, progressively,
to the pool of moves which are to be considered;
whereas I use progressive
I guess I'm not really appreciating the difference between node value
prior and progressive bias - adding a fixed small number of wins or
diminishing heuristic value seems very similar to me in practice. Is the
difference noticeable?
It just means that the weight of the prior does not
IEEE Transactions on Computational Intelligence and AI in Games
Special Issue on Monte Carlo Techniques and Computer Go
Special-issue editors: Chang-Shing Lee, Martin Müller, Olivier Teytaud
In the last few years Monte Carlo Tree Search (MCTS) has
revolutionised Computer Go, with MCTS programs
Before monte carlo I spent a couple of years writing and tuning an
alpha-beta searcher. It's still in there and I ship it to provide the
lower
playing levels. Alpha-beta with limited time makes much prettier moves
than
monte carlo.
Would there be interest in a paper that compares the
As always, all players, however weak, are welcome. There are in fact some
strong entrants for this event, but they will not mind at all having some
weaker opponents - the more the better, particularly in this fast
tournament
with 15 rounds. Instructions for entering are at
Independently of you own view I consider MoGoBot to be a very
interesting participant in the tournament.
It's really a trial for MoGoTw :-) the name is mogobot1 because I've
kept the same KGS account, but mogotw is not mogo.
In my eyes, besides MoGo, MFoG, and Zen
only Fuego and Valkyria are
We added (MoGo's original) patterns and RAVE at about the same time. Both
helped a great deal, and using both was best of all.
You mean mogo's 3x3 patterns I guess; the discussion here is about pattern
databases for biasing the research in the tree (patterns with size until
19x19) and how they
Hi David, Thanks for these information.
Your patterns are not automatically extracted; I don't know to which extent
we would benefit
from patterns like yours in MoGo, or to which extent you would benefit from
automatically
extracted patterns as ours, and to which extent it is nearly equivalent or
Thanks for sharing all this information, David.
It would be easy to turn off rave and run some tests to do
the win rate. Would take about a day to get significant
results. I think RAVE still helps a lot.
I agree that it's easy to turn off rave, but I think that for a fair
comparison
you
/
--
=
Olivier Teytaud (TAO-inria) olivier.teyt...@inria.fr
Tel (33)169154231 / Fax (33)169156586
Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS - Universite Paris-Sud),
bat 490 Universite Paris-Sud 91405 Orsay Cedex France
(one of the 56.5 % of french who did not vote for Sarkozy in 2007
If none, fill_board: pick a random empty point. If it is not on the 1st or
2nd line and there are no stones in 8 adjacent points, play it
We repeat this several times, but this does not explain why it does not work
for just a single time.
The main weakness in your experimental setup is that
Hmm. It will take quite a while to run a few thousand games with 200K
playouts, and I might need a stronger opponent, but I’m trying it now.
Yes, I know it takes time :-) by the way it was already significantly
efficient at 100 000 sims / move. I don't know the result for 50 000 but
perhaps
. Pebbles has a Mogo playout design, where you check
for patterns only around the last move (or two).
In MoGo, it's not only around the last move (at least with some probability
and when there are empty spaces in the board); this is the fill board
modification.
(this provides a big
Just to clarify: I was not saying that Mogo's policy consisted
*solely* of looking for patterns around the last move. Merely that
it does not look for patterns around *every* point, which other
playout policies (e.g., CrazyStone, if I understand Remi's papers
correctly) appear to do. The RL
On
http://www.lri.fr/~gelly/MoGo_Download.htmhttp://www.lri.fr/%7Egelly/MoGo_Download.htm,
under the FAQ section,
I found the bullet point:
MoGo continues playing after the game is over?: MoGo never consider
a pass unless you pass first. If you think the game is over, simply
pass.
Is
There has been some talk here of using a zero exploration coefficient. Does
this literally mean using the win ratio (with one dummy win per node) to
decide paths through the MC tree? It seems that the best move could easily
be eliminated by a couple of bad runs.
Does this only work when using
In my humble opinion, we need a change in the algorithm. The numbers are
misleading - 95% of win of
MoGo on 32 nodes against MoGo on 1 node (this is a real number for 19x19)
certainly means that the
parallel version is stronger than the sequential version, but not much
better, far less than what
://www.computer-go.org/mailman/listinfo/computer-go/
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
--
=
Olivier Teytaud
But, while that may be the case, perhaps we can say that they are
hitting a wall in their observable playing strength against non-MCTS
players (such as humans) at higher levels. In [2] I touched upon how the
nature of the game changes at higher levels, and how scaling results
obtained
Perhaps I'm mistaken in my reading, but isn't Mogo a clusterized and highly
tuned version of gnugo? Things like that made me want to make this post. As
I find the Go programming community more open to sharing ideas and code than
my chess world counter part.
Will gladly stand corrected w/
http://www.gokgs.com/gameArchives.jsp?user=mogoRennes
Taranu won the first three games and lost the final one.
So, the score was 3-1 for him.
Thanks for the report. As far as I know (not completly sure) it's the first
win (in 9x9 game komi 7.5) of a computer against a human as black. I
Did you verify that Mogo would have played those stupid fast moves
correctly without having to add too much time?
No, I've not checked. But the moves were really fast and
the comments of humans were in that direction.
I agree that we must have more (much more) time for early move. But for
When Mogo runs on the supercomputer with long-ish time limits, how big does
the search tree get?
Plotting the depth/number of nodes as a function of the thinking time might
be a good idea... No idea :-( I just remember that changing the number of
visits before adding a new node in the tree
Theorem: In a finite game tree with no cycles, with binary rewards, the UCT
algorithm with c==0
converges (in the absence of computational limitations) to the game
theoretic optimal policy.
This is also tree with RAVE instead of UCT, if you ensure that RAVE values
are never below some
Hi.
For your email about newer versions of MoGo;
technically, the main differences with version 3 are:
- use of MPI (useless unless you have a cluster);
- opening books in 9x9;
- more go-expertise
- better exploration term (not UCT-like)
- much stronger handling of patterns in the tree part
-
The game can be found here http://www.lri.fr/~teytaud/H7.sgf
or on KGS, for user mogo.
I'm posting these results, but I must precise that I was not operating
myself - Arpad Rimmel did operate, and Guillaume Chaslot was also very
involved in the preparation. MoGo was running on Huygens (in
Well, empirically, when I set the exploration component to zero it starts
to play a lot worse. Like I wrote: the winning percentage drops to 24% vs.
the same program with the exploration component, which is a huge difference.
So if you have a different experience, you must have something
I'd like to make sure I understand what you mean exactly. You use some
heuristics to intialize all the moves (or maybe some of the moves) with a
certain win-loss and rave-win-loss ratios?
Not only ratios, but also numbers of simulations. Thanks to patterns, expert
rules.
To a certain
Of course you can do put much more clever prior if you are a player and
know the subtleties of the game.
E.g. patterns extracted from databases - but it's not enough, carefully tune
the coefficients for empty triangles (important!) and various other
importants patterns/rules (don't just keep
Well, now mogo has an exploration term - but not at all UCB-like.
I was talking about times where I was still there ... ages ago :)
Good old times :-)
you've been helpful several times even from far away :-)
___
computer-go mailing list
I don't know the answer, but it's not too surprising - with random play
the komi should be something like 2 or 3, so white with 7.5 komi has a
pretty good advantage. This advantage disappears (or almost
disappears) if the games are well played, but in your case they are
not.
I think
In the computer-Go event of Clermont-Ferrand,
MoGo played four 9x9 games, plus blitz games,
against Motoki Noguchi (chinese rules, komi 7.5);
the result is a draw - the games are presented and discussed in
http://www.lri.fr/~teytaud/crClermont/cr.pdf
Best regards,
Olivier
Thank you for writing this very interesting report. But it's a 40Mb pdf
file, my Internet Explorer can't handle it at all, and my FireFox only
with difficulty. A more accessible version, perhaps without the
high-resolution pictures, might reach more readers.
Sorry for that :-)
I think it's now well known that Mogo doesn't use UCT.
I realize that i have no idea at all what Mogo do use for
it's MCTS.
A complicated formula mixing
(i) patterns (ii) rules (iii) rave values (iv) online statistics
Also we have a little learning (i.e. late parts of simulations
are evolved
Is there any theoretical reasons for the Mogo Opening being built out of
self play, rather than by spending time increasing the number of
simulations
at the root, and after a time, keeping what seems to be the best ?
There are practical reasons: our approach can be used with humans or
By conjecture, i suppose you mean that
no experiments yet has been ran as
to assess this hypothesis ?
Yes. The other reasons were sufficient :-)
I think Sylvain (and maybe just everyone else) has tried
at some point to use a UCT decision bot, as a way to
get the simulation done. Then
It's only a matter of time before MoGo becomes self-aware and destroys us
all. ;)
By the way, during the IAGO 2008 (meeting between mogo and Catalin Taranu),
a very angry guy came during the preliminary games against amateur players
and shouted that we were mixing war and art, and plenty
of
I think it was the surprisingly useful combination of UCT with Monte-Carlo
that got the attention of the 'old school' Go programmers.
I would say Monte-Carlo + Tree Search rather than Monte-Carlo + UCT. You
can have a very strong program without UCT.
You can't without the incremental tree +
It's also possible that when David says lite playouts he means
something heavier than what we think.I doubt even Mogo's heavy
playout resembles strong play but is simply tuned with some knowledge
that can be implemented in reasonable time.
Our heaviest playouts are slower but not not
You have to distinguish several scenarii when maximizing
the playing strength/value of your Go program:
(a) auto-play (or play between different versions of your prog)
(a') play against other computer programs
(b) play against humans
(c) program as tool for human analysis of Go positions or
My congratulations also to David :-) and good luck for both
MoGo and Leela for the silver medal in 9x9 :-)
Olivier
Many Faces of Go has won also the 19x19 competition
in the 13th International Computer Games Championships,
with a 100 % score. The silver medal goes to MoGo (only
loss
/listinfo/computer-go/
--
=
Olivier Teytaud (TAO-inria) [EMAIL PROTECTED]
Tel (33)169154231 / Fax (33)169156586
Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS - Universite Paris-Sud),
bat 490 Universite Paris-Sud 91405 Orsay Cedex France
Mogo was allowed to use 800 cores, not more, and only for games against
humans.
We have no acces to so many cores for computer-computer games (if there were
only three teams involved,
we could :-) ).
For some games Huygens was unaivalable at all, and mogo played with much
weaker hardware (some
For the use of fast networks:
yes, fast networks improve the results, in particular for 9x9, in my humble
opinion - however, you have already a good speed-up without
that, in particular for 19x19, and in particular if you have multiple cores
per node so that one core can take care of
Dear all,
the results of the 9x9 computer-go event in Taiwan (including a 9x9
competition and games between humans and computers)
can be seen at
http://go.nutn.edu.tw/eng/main_eng.htm
(see news)
These games were organized by the National University of Tainan and the
Chang Jung Christian
- There had been a TV program of professional 9x9 Go for years (some
member of this list have the records of the games played in this
program). Takemiya 9p and Yuki 9p were the strongest.
I'm afraid the answer is no, but:
are these records free and available somewhere ?
Thanks for your
Yes. I use Sylvain's fpu and decrease it a little before starting a
simulation, say, fpu *= 0.99. This is very simple and fast.
Ok. Perhaps I'm wrong (I might misunderstand your solution and I might be
wrong
whenever I've understood :-) ); but
- I think that this does not avoid
Although I'm parallelizing in not SMP systems but a cluster of loosely
coupled (small) computers connected through moderate speed networks
using broadcasting positions, this may not change the vlaue of
avoiding redundancies. I'll study more when implementing
pre-knowledge or some. Thanks.
MC is playing most goal-directed (zielgerichtet
in German) when the position is balanced or when
the side of MC is slightly behind. However, when
MC is clearly ahead or clearly behind it is playing rather
lazy.
At some point we were investigating that here, but only on small sets of
games
I made a change over the weekend, which looks like it makes 9x9 150 ELO
weaker and 19x19 over 200 ELO stronger.
We have plenty of size-dependent parameters and plenty of if
(boardsize==19) in MoGo for things like that :-)
___
computer-go mailing list
mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
--
=
Olivier Teytaud (TAO-inria) [EMAIL PROTECTED]
Tel (33)169154231 / Fax (33)169156586
Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS
The bright side here is that 9x9 is not really important but just
a test bed. If it works for 19x19, that's good.
People moderately intested in Go could also claim that both 9x9 and 19x19
are
just testbeds for power plant management :-)
In my humble opinion, both are intesting, both as
By my recent experiments, 8~9 * (threads - 1) ELO is lost. This
matches my earlier result well.
Do you have tricks for avoiding redundancies between simulations ?
I suggest simple tricks like do not go to node X if there is a thread
currently in node X
(simply by setting the score of the
Yes, and then 19x19 with handicap.
On Aug 25, 2008, at 10:47 PM, Olivier Teytaud wrote:
Just for information, mogo will play in a few minutes (on Kgs /
computer-go) some games
against high level humans.
MogoTitan is playing 9x9 against nutngo ?
Christoph
and the player :-)
Best regards,
Olivier for the mogo-team
Yes, and then 19x19 with handicap.
On Aug 25, 2008, at 10:47 PM, Olivier Teytaud wrote:
Just for information, mogo will play in a few minutes (on Kgs /
computer-go) some games
against high level humans.
MogoTitan is playing 9x9
Kim :-) ).
Best regards,
Olivier
--
=
Olivier Teytaud (TAO-inria) [EMAIL PROTECTED]
Tel (33)169154231 / Fax (33)169156586
Equipe TAO (Inria-Futurs), LRI, UMR 8623(CNRS - Universite Paris-Sud),
bat 490 Universite Paris-Sud 91405 Orsay Cedex
1 - 100 of 188 matches
Mail list logo
