[resending; apologies if you get this twice.]
Hi,
This is my first post to the list, so I'll introduce myself: I'm a
software developer and just getting started with playing Go. I read
the article in the Economist and thought that the work on Monte-Carlo
based Go programs sounds promising.
management.
Maybe it's just a difference in processors? It's a two core chip but
perhaps not as fast at single-threaded apps. Adding multithreading
might help.
- Brian
On 2/21/07, Łukasz Lew [EMAIL PROTECTED] wrote:
On 2/21/07, Brian Slesinsky [EMAIL PROTECTED] wrote:
[resending; apologies if you
?
I've made some tests on 2 core processors, and I have strange results.
Some of 2 core processors got results exactly 2x times worse than they should.
Why?
I have no idea.
But 2.8 Ghz 2 core works exactly like my 1.4 laptop.
Also version of g++ does matter.
Łukasz
On 2/21/07, Brian Slesinsky
I wonder whether you could save time by not doing this during the
opening? It seems like ownership maps will be meaningless for opening
moves and gradually become more important the closer you get to the
end. It would be interesting to see how many moves into the game you
have to be before it
On 3/14/07, Darren Cook [EMAIL PROTECTED] wrote:
P.S. Is anyone using C# on linux? I thought C# was standardized so I
expected to find something, but google is only giving me articles from
2001...
I haven't used it, but the Mono project has reimplemented C# and many
of the .Net platform
I've been lurking on the list for a while, thinking about how to make
a contribution to computer go in the limited time I have. Perhaps
others are in the same situation?
It seems like there is still a fair amount of reinventing the wheel
that needs to be done just to get started on a go engine.
Maybe try this test with libego?
Don Dailey:
I have one interesting test that I do, which I take
with a grain of salt, but I use as a first guess estimate. I search
from the opening position a few hundred times and average the time
required to find the move e5.My assumption is that e5 is
Going along with this, the numbers won't add up (although I don't know
if that is important.) In other words, if you do 10,000 simulations at
the root, all grandchildren will add up to more (due to transpositions.)
If you propogate this up the tree you might come up with many more than
10,000
On 5/11/07, Jason House [EMAIL PROTECTED] wrote:
Consider a node who's had one child extensively evaluated through
transpositions. When UCT does come to visit it, the sqrt(sum(child
simulations)) will be very high. That will artificially favor exploration
of children with less simulations.
I think there is something to this; it seems like it should be
possible to use a database of randomly selected positions from games
along with the best known followup, and use that as a faster way of
testing a program's strength than playing full games. Such a database
would be valuable for all
This is very interesting. I've skimmed so far and don't understand
everything yet, but I can make some comments on readability.
Table 1 takes some study to understand. If I understand it correctly,
the Feature column might be more clearly labeled Feature of Candidate
Move. (For example, Pass
Have you noticed a difference between Java 5 and 6? I've heard some
programs get a nice boost.
- Brian
On 5/25/07, Peter Drake [EMAIL PROTECTED] wrote:
For what it's worth, I'm getting over 25k playouts per second in Java on my
4-core 3GHz machine using Orego.
Single easiest improvement: use
With repeat-winners, if there is a move is seems flawless at first but
some flaw is eventually found, there might be a rough transition once
the flaw is identified, since there is no backup plan. It might make
more sense to study two apparently flawless children equally until a
flaw is found in
Maybe another way to put it:
In Fischer time, the time allowed to play the game is simply a
function of the number of moves in the game. If white moves last,
this time is same for both players, otherwise black gets slightly
more. At the beginning of the game, the time on the clock is the
I wonder whether the use of games as a metaphor would make general
machine learning concepts more easily understood by non-specialists?
That is, if you took a machine learning paper and rewrote it in terms
of games, would that make it easier or harder to understand for people
unfamiliar with both
It seems to me that a domain where everything is so amateuristic has
its advantages, if you can only see them. Here is a field that is
small enough that most people know each other and anyone can
contribute with a certain amount of effort. These are the early days;
computer go's best years are
On 7/9/07, David Fotland [EMAIL PROTECTED] wrote:
Very unlikely. I'm a strong player (but not very strong - 3 dan amateur),
and I've played perhaps a dozen 9x9 games with people who were just learning
the rules. I played in a couple of 9x9 tournaments on the crazy go day at
the go congress
This discussion reminds me of a naive theory that I sometimes wonder about:
Since the players in the playouts are so weak, it seems like the
improving the ability to defend a strong position from a
not-very-clever move (and not lose it via a blunder) should be more
important than improving the
On 7/10/07, Jacques Basaldúa [EMAIL PROTECTED] wrote:
When you favor defense (or attack) you may think: This is unbiased
since some times it favors black and other times it favors white But
the fact is when black is in danger at the root of the tree, it is in
danger in most of the tree,
On 7/11/07, Jacques Basaldúa [EMAIL PROTECTED] wrote:
I will try to explain it better: E.g. The game is in a position where black
is in danger. That position is the root node. All stones in the root node
are inherited in any node below, except when they are captured. Your trick
pretends to
From discussion, it seems that there are two important tests of
unbiasedness that we can make for an improvement to playouts:
1: For any position, we should equally study what happens when either
black or white moves there. This is captured in the proverb your
opponent's good move is your good
What does everyone think about setting up an archive for the
computer-go mailing list on Google Groups? This would allow better
searching of archived messages than with the current archives.
(I don't know a good way to upload messages from the current archive,
so it would only include messages
On 7/18/07, Nick Wedd [EMAIL PROTECTED] wrote:
Are you proposing replacing this mailing list by a usenet group? Or is
there a way that you can get Google Groups to archive something that is
not part of usenet?
There are actually two kinds of Google Groups. Some are traditional
Usenet groups
On 7/21/07, chrilly [EMAIL PROTECTED] wrote:
If you feed more data/games
the quality of prediction increases. It is in fact a weakness of the
Elo-Rating that this is not taken into account (newer systems like TrueScore
do).
Can you provide a link to TrueScore? My searches are coming up empty.
Okay, if nobody has any objections, I'll go ahead and set up the
archive. Also, I should confess to an ulterior motive: I actually
work at Google, but I haven't used Google Groups much, so this is
partly an exercise in learning more about how it works.
The first step was to find the
Do you have a 20% project related to Go? It would be fun the see the
results of UCT on some massive Google hardware. Can you get me a job?
I'm not working on anything Go-related at the moment. My 20% time is
oversubscribed; too many ideas, not enough time. But yes, it would be
a cool thing
The archive is up and running at:
http://groups.google.com/group/computer-go-archive
It won't be very interesting until more messages have been archived.
- Brian
___
computer-go mailing list
computer-go@computer-go.org
It seems like adaptation in the context of a game of Go just making
the best response to the opponent's move, however unexpected. So, if
there were such a thing as a perfect Go player, it would have no need
to learn, but it would be perfectly adaptive, in this context.
Of course, one could also
On 7/26/07, Jeff Nowakowski [EMAIL PROTECTED] wrote:
Ah, an opponent model. Where's the poision?
http://www.imdb.com/title/tt0093779/quotes#qt0250635
Too much rock, paper, scissors in poker for my tastes.
BTW, there's a rather sophisticated Rock Paper Scissors player named
Iocane Powder.
Congratulations. Are there any plans to release the source? Perhaps
someone else will figure out how to port it.
- Brian
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
On 9/9/07, Sylvain Gelly [EMAIL PROTECTED] wrote:
Perhaps someone else will figure out how to port it.
Well, it actually builds and work on windows, only the speed is an
issue. I should try if the speed is the same on linux with such an old
compiler. My guess is that it is really a matter of
Thought I'd emphasize this point:
Don Dailey:
I spend a great deal of time waiting on the computer, because I have no clue
what will work and I must test it.
This makes Go programming somewhat unusual; for a lot of programs, you
can arrange so that compiling and running your tests only takes
Thought I'd announce that I've ported the Java refbot to the Go
language (with some modifications).
I'm getting about 10,000 random playouts/second on 9x9 using a single
thread on a 32-bit iMac, using the gc compiler, which doesn't do any
optimization. I suspect that a board structure that
I'd like to, but I can't find it. Where do I download it?
2009/12/12 Don Dailey dailey@gmail.com:
That's awesome!
Do you have performance numbers on the same hardware for the C refbot?
- Don
On Sat, Dec 12, 2009 at 7:39 PM, Brian Slesinsky br...@slesinsky.org
wrote:
Thought I'd
,
my D port of the java refbot was within about 1%
Sent from my iPhone
On Dec 13, 2009, at 12:01 AM, Brian Slesinsky br...@slesinsky.org wrote:
I'd like to, but I can't find it. Where do I download it?
2009/12/12 Don Dailey dailey@gmail.com:
That's awesome!
Do you have performance
On Sun, Dec 13, 2009 at 2:56 PM, Darren Cook dar...@dcook.org wrote:
Do you mean you added the array to Gongo or to the java version? I.e. is
Gongo twice as quick as the java version because the java version is
doing more, or twice as quick even though it is also doing more?
Gongo is faster
I probably won't have time to look at it much, but it would be good to
have another Java refbot to compare against. I did look at Plug-and-Go
but the install seems a bit tricky since I don't use Eclipse or
Spring. Ideally, each engine should compile to a jar file that
provides a GTP interface when
I'm a bit confused by the difference between RAVE and AMAF. Or are
they the same thing?
- Brian
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
Okay, I added a few more timings (playouts / second, very rough):
Plug-and-Go refbot: 14700
CRef bot (-O3) 12500
Gongo 1
Java bot: 6500
CRef bot (no optimization) 5882
Note that Gongo and Plug-and-Go are using different board data
:
The relative values look about right. But I remember getting much
higher numbers. Did you run the Java versions with or without the
-server parameter?
Mark
On Mon, Dec 14, 2009 at 11:00 PM, Brian Slesinsky br...@slesinsky.org wrote:
Okay, I added a few more timings (playouts / second, very rough
How about creating an account on github and uploading it there?
2009/12/30 Christian Nentwich christ...@modeltwozero.com:
All,
the CUDA light playout code I wrote earlier this year and posted about in
this list is lying around dead on my hard disk, and I am not looking to take
it
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?
On Fri, Jan 15, 2010 at 9:50 AM, Brian Sheppard sheppar...@aol.com wrote:
I recommend the paper
http://hal.inria.fr/docs/00/36/97/83/PDF/ouvertures9x9.pdf by the
42 matches
Mail list logo
