i think that it's an accurate statement.
it certainly hasn't already played such a role, and there is
no evidence that it will or can.
s.
- Original Message
From: Chris Fant [EMAIL PROTECTED]
To: computer-go computer-go@computer-go.org
Sent: Wednesday, October 10, 2007 9:15:18 PM
In your own paper you say:
At the 19x19 level, Monte Carlo programs are now at the level of the
strongest traditional programs.
[https://webdisk.lclark.edu/drake/publications/GAMEON-07-drake.pdf]
And MC programs are more scalable that traditional programs. That
seems like some evidence that it
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Let's cut to the chase and the real issue:
Monte Carlo techniques have recently had success in Go played on a
restricted 9-by-9 board. My hunch, however, is that they won't play a
significant role in creating a machine that can top the best human
There is no restriction on how many mogo bots can run. However, there
is not much of a point if everyone is just running the same bot unless
they are running at different levels and we can see exactly how they are
set up.
We have launched 4 mogos, and I explain here what is tested:
-
This may be the same Chris Rosin:
http://www.cs.wisc.edu/areas/ai/aisem/abstracts/1995.2.summer/rosin.html
http://www-cse.ucsd.edu/users/crosin/
Other than the senseis.xmp reference, I have been able to google nothing about
greenpeep.
Terry McIntyre [EMAIL PROTECTED]
- Original Message
On 10/9/07, Andrés Domínguez [EMAIL PROTECTED] wrote:
2007/10/9, Eric Boesch [EMAIL PROTECTED]:
Naive null move is unhelpful because throughout much of a go game,
almost every move is better than passing,
I think this is not the point of null move. Null move is if pass is good
enough
to
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Several points:
Null move is usually applied to a beta cutoff - but of course this is
mostly semantics. In the literature if you can pass (play the null
move) and still get a beta cutoff then you are in a fruitless line of
play because your opponent
I agree. Computer go needs someone who will play large tournaments are
publish results. I'm also curious how Many Faces would do against Mogo on
19x19 in a long match. Mogo is much better at endgames, and is much
greedier, but Many Faces is much stronger tactically. Certainly if there
were
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
David Fotland wrote:
I agree. Computer go needs someone who will play large tournaments are
publish results. I'm also curious how Many Faces would do against Mogo on
19x19 in a long match. Mogo is much better at endgames, and is much
greedier,
- Original Message
From: Don Dailey [EMAIL PROTECTED]
My point is that this probably won't happen in computer Go but it
happened long ago in computer chess.
- - Don
Can you point us to info about comparable agency for computer chess? Who funds
such an agency?
Thanks!
Don Dailey wrote:
I believe Many Faces is probably stronger than Mogo but I don't know
that this has been proven.
Hi Don,
I'd bet on Mogo. In case nobody noticed, Crazy Stone won a match against
KCC Igo this summer, with 15 wins and 4 losses. The match was organized
by Hiroshi Yamashita.
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
All I need is a linux machine with a good internet connections and we
can set up this match.
We won't be proving anything because obviously Mogo will be better if
you choose the right hardware (since MFGO that David will run is fixed.)
But at least
At least for Many Faces 11, if you run it at the top level, it will play the
same no matter what hardware you use since the search parameters are fixed.
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Don Dailey
Sent: Thursday, October 11, 2007 10:33
On Thu, 11 Oct 2007, Don Dailey wrote:
Right now we know that Mogo dominates in 9x9. Without CGOS this would
be speculation based on who won the last tournament. But CGOS is not
the right way although it's a useful tool.There needs to be some
kind of testing agency that is fair and
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Good common sense answer. I agree that this could be settled.
I'll go ahead and help Chris Fant set up a the server which he will
administer.
Meanwhile, can you experiment with the 9x9 server just to see if you can
get it working on CGOS?You
On Oct 11, 2007, at 10:44 AM, terry mcintyre wrote:
- Original Message
From: Don Dailey [EMAIL PROTECTED]
My point is that this probably won't happen in computer Go but it
happened long ago in computer chess.
- - Don
Can you point us to info about comparable agency for computer
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Olivier Teytaud wrote:
I'd connect Crazy Stone to CGOS if Many Faces is there.
Mogo will be there also; a 19x19 Cgos would be very interesting
in my humble opinion.
But we had a 19x19 server and it WAS NOT interesting. Nobody seemed
willing
I'd connect Crazy Stone to CGOS if Many Faces is there.
Mogo will be there also; a 19x19 Cgos would be very interesting
in my humble opinion. The only drawback of Cgos for me is that
we have no idea (at least, I have no idea) of the equivalence
with human standards (kgs rankings are much easier
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
I thought Monte Carlo plays and thinks MORE like human players. That
might make them easier to beat, I don't know. Playing like a human
doesn't imply they are harder to beat. I have heard people complain
that they couldn't beat the early chess
Yeah, let's get it up tonight (in three hours). I can't give you an
account, but I can administer it.
On 10/11/07, Don Dailey [EMAIL PROTECTED] wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Olivier Teytaud wrote:
I'd connect Crazy Stone to CGOS if Many Faces is there.
Mogo
I already have experimented with the 9x9 server with an anonymous name :)
The results have aged off the server, but I think it had a rating between
1750 and 1850. So I had working GTP code about 8 months ago. I'll give it
a try today on 9x9 to see if it still works.
-Original Message-
On Thu, 11 Oct 2007, Don Dailey wrote:
I appreciate the vote of confidence, but my point is that if you want
some kind of certified rating CGOS is not a good choice. You can run
anything on CGOS and claim anything. You could even substitute a
strong human player, if you wanted to.
The problem with a closed system where the tournament director
controls both of the machines is that it precludes programs like mine,
SlugGo, that intrinsically use multiple CPUs and run on Macs rather
than Windows or Linux boxes.
Cheers,
David
On 11, Oct 2007, at 12:15 PM, Don Dailey wrote:
I'd say that the CGOS server has been an invaluable spur to development, since
it does allow fairly easy testing against the competition.
What Don seems to be proposing is a way of standardizing the hardware - all
programs run on the same platform.
It seems that this would require an
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
David Doshay wrote:
The problem with a closed system where the tournament director
controls both of the machines is that it precludes programs like mine,
SlugGo, that intrinsically use multiple CPUs and run on Macs rather
than Windows or Linux
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
In the computer chess ratings they don't necessarily use identical
machines, the idea is to simply publish each player as a
software/hardware combo.You will see for instance that some programs
were tested on a variety of hardware.
Which in itself
On Thu, 11 Oct 2007, Don Dailey wrote:
But we had a 19x19 server and it WAS NOT interesting. Nobody seemed
willing to play on it.
Maybe that has changed now.
It was not interesting because there was only one competitive
program on it (MoGo). Most people's programs are too weak
at 19x19, but
Can we also count on Steenvreter for this 19x19 smack-down? You out
there, Erik?
On 10/11/07, Eric Boesch [EMAIL PROTECTED] wrote:
On 10/11/07, David Fotland [EMAIL PROTECTED] wrote:
But the only way to settle this is to do some experiments. I could
certainly be wrong. If we have a
Hi - yes, that is me, and greenpeep is my program. About 10 years ago
I worked on coevolution applied to Go, but greenpeep is an
entirely new program based on UCT. I think the greenpeep is mostly
similar to what some other people are doing with UCT, and I'm using
it to test ideas. greenpeep
On Oct 11, 2007, at 1:49 PM, Eric Boesch wrote:
On 10/11/07, David Fotland [EMAIL PROTECTED] wrote:
But the only way to settle this is to do some experiments. I could
certainly be wrong. If we have a mogo-many faces match on 19x19
cgos, and
we also have them play for ratings against
Yes I'm here :-) Sorry to have to disappoint you though, I have not
yet found enough time to work on 19x19. For now the throne rightfully
belongs to Mogo.
Erik
On 10/11/07, Chris Fant [EMAIL PROTECTED] wrote:
Can we also count on Steenvreter for this 19x19 smack-down? You out
there, Erik?
Then they are stronger than many face against people. I think Many Faces
would be around 4k to 6k.
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Eric Boesch
Sent: Thursday, October 11, 2007 1:50 PM
To: computer-go
Subject: Re: [computer-go]
Someone already did: Stone eater.
On 10/11/07, terry mcintyre [EMAIL PROTECTED] wrote:
Erik,
It would be great to see Steenvreter on the 9x9 cgos server. BTW, can you
translate Steenvreter for us English speakers? Thanks!
From: Erik van der Werf [EMAIL PROTECTED]
Yes I'm here :-) Sorry
One thing computer chess has had for a very long time and is practically
absent in Go is a rating list. It's always been possible to identify
who the best programs and where they stand relative to any other. There
are agencies that play hundreds of thousands of games constantly to
track
On Thu, 2007-10-11 at 18:37 -0400, Chris Fant wrote:
Someone already did: Stone eater.
On 10/11/07, terry mcintyre [EMAIL PROTECTED] wrote:
Erik,
It would be great to see Steenvreter on the 9x9 cgos server. BTW, can you
translate Steenvreter for us English speakers? Thanks!
Eater
I think that there's an apples/oranges thing going on here.
My hunch, however, is that they won't play a
significant role in creating a machine that can top the best human
players in the 19-by-19 game.
i agree with this statement.
And MC programs are more scalable that traditional programs.
Does anyone have a good reference for reading the notation in the
Gelley/Shriver paper Combining online and offline knowledge in UCT?
___
computer-go mailing list
computer-go@computer-go.org
http://www.computer-go.org/mailman/listinfo/computer-go/
Hi greenpeep aka chris,
My program GGMC Go ver. 2, rated around 2000 ELO now, runs abut 25k
playouts/s on 4-core box and do 360k playouts/move at most on cgos
(and last KGS tournament as well). It's based on MoGo's first
report, though its framework is different.
# I'll add some features but
From: Christopher Rosin [EMAIL PROTECTED]
Christopher, Thanks for your explanation of greenpeep!
megasnippage
- Biasing playouts by patterns is much better than unbiased playouts
- Playouts using self-play patterns together with MoGo-style move
preferences (favor defensive moves and
Reinforcment Learning: A Survey is available on citeseer.
/Dan Andersson
Ursprungligt meddelande
Från: [EMAIL PROTECTED]
Datum: 2007-okt-12 02:18
Till: computer-gocomputer-go@computer-go.org
Ärende: [computer-go] Combining online and offline knowledge in UCT
Does anyone have a good
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi Steve,
So this doesn't get too lengthy I'll remove the stuff I'm not responding
to.
I think this statement is more or less true. Didn't you see the
scalability data for 19x19? In fact didn't you help me produce it?
we tested some very
Considering how monte carlo actually works, I think it's plausible
to argue that it works best where the distance to endgame is small.
For a 19x19 board, the playing speed may be only a factor of 4 worse,
but the effective learning speed for an opening position might be
exponentially worse. In
42 matches
Mail list logo