r Pachi CGOS setup with others if you find a good one I think.
Petr Baudis, Rossum
___
Computer-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-go
> > > inline file
> > >___
> > >Computer-g
-minute addition", is imho
apparent even in the text of the Nature paper.
Also, the 3-day version simply had roughly similar training time
available as AlphaZero did.
--
Petr Baudis, Rossum
Run before you walk! Fly before you crawl! Keep moving for
nse as the best
policy improvement operator?
What would you say is the current state-of-art game tree search for
chess? That's a very unfamiliar world for me, to be honest all I really
know is MCTS...
--
Petr Baudis, Rossum
Run before you walk!
On Fri, Nov 10, 2017 at 03:40:27PM +0100, Gian-Carlo Pascutto wrote:
> On 10/11/2017 1:47, Petr Baudis wrote:
>
> > * AlphaGo used 19 resnet layers for 19x19, so I used 7 layers for 7x7.
>
> How many filters per layer?
256 like AlphaGo.
> FWIW 7 layer resnet (14 + 2 la
On Fri, Nov 10, 2017 at 01:47:17AM +0100, Petr Baudis wrote:
> This is a truly "zero-knowledge" system like AlphaGo Zero - it needs
> no supervision, and it contains no Monte Carlo simulations or other
> heuristics. But it's not entirely 1:1, I did some tweaks which I th
t surpass GNUGo quickly at this point? Also this late
improvement coincides with the increased simulation number.
At the same time, Nochi supports supervised training (with the rest
kept the same) which I'm now experimenting with on 19x19.
Happy training,
--
ps://github.com/pasky/michi/tree/nnet for the time being, but maybe
I'm missing some good reason to use MSE instead?
Thanks,
--
Petr Baudis, Rossum
Run before you walk! Fly before you crawl! Keep moving forward!
If we fail, I'd
KGS bot tournaments.
>
> Nick
> --
> Nick Wedd mapr...@gmail.com
--
Petr Baudis, Rossum
Run before you walk! Fly before you crawl! Keep moving forward!
If we fail, I'd rather fail really hugely. -- Moist von Lipwig
_
On Fri, Oct 20, 2017 at 08:02:02PM +, Gian-Carlo Pascutto wrote:
> On Fri, Oct 20, 2017, 21:48 Petr Baudis wrote:
>
> > Few open questions I currently have, comments welcome:
> >
> > - there is no input representing the number of captures; is this
> > i
, 2017 at 03:23:49PM +0200, Petr Baudis wrote:
> I tried to reimplement the system - in a simplified way, trying to
> find the minimum that learns to play 5x5 in a few thousands of
> self-plays. Turns out there are several components which are important
> to avoid some obvious a
ct 19, 2017 at 02:23:41PM +0200, Petr Baudis wrote:
> The order of magnitude matches my parameter numbers. (My attempt to
> reproduce a simplified version of this is currently evolving at
> https://github.com/pasky/michi/tree/nnet but the code is a me
rrect?
>
> Álvaro.
>
>
>
> On Thu, Oct 19, 2017 at 6:17 AM, Petr Baudis wrote:
>
> > On Wed, Oct 18, 2017 at 04:29:47PM -0700, David Doshay wrote:
> > > I saw my first AlphaGo Zero joke today:
> > >
> > > After a few more months of sel
tempt to reproduce AlphaGo Zero
yesterday converged to overnight. ;-) But I'm afraid it's because of
a bug, not wisdom...
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://comp
On Fri, Aug 18, 2017 at 06:31:54PM +0200, Gian-Carlo Pascutto wrote:
> On 18-08-17 16:56, Petr Baudis wrote:
> >> Uh, what was the argument again?
> >
> > Well, unrelated to what you wrote :-) - that Deep Blue implemented
> > existing methods in a cool applica
to do. I liked Andrej
Karpathy's summary on this:
https://medium.com/@karpathy/alphago-in-context-c47718cb95a5
--
Petr Baudis, Rossum
Run before you walk! Fly before you crawl! Keep moving forward!
If we fail, I'd rather fai
of go
> > at all, not even "roughly".
> >
> > /Gunnar
> > ___
> > Computer-go mailing list
> > Computer-go@computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
>
> __
.
--
Petr Baudis, Rossum.ai
Run before you walk! Fly before you crawl! Keep moving forward!
If we fail, I'd rather fail really hugely. -- Moist von Lipwig
___
Computer-go mailing list
Comput
is mildly
horrifying for me - hopefully it will indeed happen only to emails from
DMARC-reject domains. Thanks for the pointer!
--
Petr Baudis
Run before you walk! Fly before you crawl! Keep moving forward!
If we fail, I'd rather fail
weaker in general) when given
the "maximize_score" parameter. I wonder if other programs also have
multiple modes like this.)
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
ex
semeai correctly, or if it just "sensed".
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
gt; Observe: this is not the Zen that will play against
> Luks Kraemer in the codecentric Challenge (from tomorrow on).
Silly question - why not? (Assuming this seems to be the strongest Zen
so far.)
Thanks,
Petr Baudis
_
ng GNUGo's
mistakes a great educational experience in the fundamental flaws of
classic engines back then.
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
_
s expanded,
i.e. less playouts made without the NN scoring in the last few
moves).
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Com
licy simple` will use this library.
> >
> >
> > Darren
> >
> > ___
> > Computer-go mailing list
> > Computer-go@computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
> >
>
On Tue, May 31, 2016 at 09:07:10AM +0200, "Ingo Althöfer" wrote:
> "Petr Baudis"
> > We still don't have a good publicly available tsumego
> > solver. I think this makes their capabilities a lot less useful for
> > game analysis.
>
> Agreed. C
the English-speaking market is very
small, and the East Asian language barrier(s) prevent a lot of network
effects to kick in; the Western audience is small and the barrier is
hard to overcome. (In the Chess world, there probably was
English-Russian barrier but the player distribution is still a lot
owser, I'd
pick OGS and it doesn't seem clear what the advantages of your server
are, possibly besides your unique rating algorithm (which I'd also love
to hear more about).
--
Petr Baudis
If you have good ideas, good data and fast computers,
as fine with using a bunch of GPUs.
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http
ature paper, they talk about GPUs, but they
could have switched to TPUs for training only after then Fan Hui matches.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/lis
o splitting them to multiple
divisions might not end up well.
Petr Baudis
___
Computer-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-go
> >
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/c
board_game
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
dare leave the
> quiet safety of the silent steppes to risk the monotonic ugly-mouthed
> egg-throwing of self-righteous smug lion camp followers snug in their
> schooled mutual hatred of anything or anyone with more melanin or a
> different perspective than their straightjacket mindset.
>
&g
twice in the article, which is
hard for me to follow).
Thanks,
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing l
(or find
the actual liberties efficiently) - and at that moment, a lot of your
earlier tricks become quite worthless.
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
e is http://ps.waltheri.net/ )
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
f truisms and not terribly informative). But I'm quite convinced that
even the first example is completely plausible.
(But I'm *not* talking about generating pages of diagrams that
describe an opening position in detail. That's to ponder when we
get the simpler things right.)
--
(My original idea was simpler, a "smarter bluetable" chatbot that'd just
generate "position-informed kibitz" - not necessarily *informative*
kibitz. Plenty of data for that, probably. ;-)
--
Petr Baudis
If you ha
an the Nature version.
But how much? We'll have a better idea when they pit it in more matches
with humans, and ideally when other programs catch up further. Without
knowing more (like the rest of the slides or a statement by someone from
Deepmind), I wouldn't personally read much into this
tinfo/computer-go
> >
> _______
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
nty that AlphaGo is significantly
better Go player than Lee Sedol at this point. What we can say with
certainty is that AlphaGo is in the same ballpark and at least roughly
as strong as Lee Sedol. To me, that's enough to be really huge on its
own accord!
--
http://www.mostlymaths.net/2010/04/my-first-port-to-ben-nanonote-gnugo.html
- you are essentially crosscompiling to javascript.
Petr Baudis
___
Computer-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-go
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/ma
on
new things! :)
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
nstance is $1800/month, while AlphaGo
single machine version uses 8xGPU, 48xCPU (and not sure what GPU
generation). So that's another computation power halving.
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost a
t might be that they found a way to replace the SL
policy with RL policy in the tree.)
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
C
, scientifically.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
:44:23PM +0200, Petri Pitkanen wrote:
> This time I think game was tougher. Though too weak to judge. At the end
> sacrifice a fistfull stones does puzzle me, but again way too weak to
> analyze it.
>
> It seem Lee Sedol is lucky if he wins a game
>
> 2016-03-10 12:39
d says, “But I think the pro will be shocked at how
> strong the program is.”
In that case it's time for Lee Sedol to start working hard on turning
this match around, because AlphaGo won the second game too! :)
Petr Baudis
___
x27;s playing
strength (or its scaling), or merely a minor tweak?
Thanks,
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Compu
Debian version is using it) to parallelize operations in threads.
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing
>
> > Test:: imagenet, 100 train iteration (batch = 256).
> >
> > * GPU: time= 260 sec / memory = 0.8 GB
> > * CPU: time= 752 sec / memory = 3.5 GiB //Memory data is from system
> >monitor.
> >
> > "
> >
> > This does not look so tre
x27;s specific problem, but in my experience,
there is no trouble at all transferring stuff between CPU and GPU - your
model is, after all, just the weight matrices. In Caffe, you should
be able to switch between GPU and CPU completely freely.
Petr Baudis
___
ent from
NVidia Keplers, but still the step up from a CPU is tremendous.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
On Sun, Feb 21, 2016 at 09:00:54PM +0100, Petr Baudis wrote:
> I'm wondering if there's some framework for studying combinatoric
> aspects of games that are not only technically Go, but also actually
> resemble real Go games played by competent players?
>
> This
one left at most 4 stones:
> The result is attached. I think there is clearly
> room for improvement, i.e. make this game much longer.
This was quite instructive, thank you very much for that!
--
Petr Baudis
If you have good i
hat yet...
My impression is that current neural networks seem to converge to
about 60%. It would be interesting if humans can still do better.
Another idea would be considering accuracy as a top N measure among
selected moves, whether it has better discernive power for currently
used models
s means that you stop the game too early if the whole board is
filled (including dame and territory) but some nakade or throwin remains
that the DCNN would like to play out, but I suspect that would pretty
much never happen in practice?
--
Hi!
On Mon, Feb 01, 2016 at 01:38:28PM +, Aja Huang wrote:
> On Mon, Feb 1, 2016 at 11:38 AM, Petr Baudis wrote:
> >
> > That's right, but unless I've overlooked something, I didn't see Fan Hui
> > create any complicated fight, there wasn't any seme
On Sun, Jan 31, 2016 at 10:16:25AM +0900, Hideki Kato wrote:
> Petr Baudis: <20160130150502.gf12...@machine.or.cz>:
> > Hi,
> >
> > it seems that Zen19X grabbed at KGS 7d and looks like it's gonna hold!
> >
> >
> > http://www.gokgs.
mego and joseki shapes is imho a simpler
explanation), leads me to believe that it remains a weakness.
Of course there are other possibilities, like AlphaGo always steering
the game in a calmer direction due to some emergent property. But
sometimes, you just have to go for the fight, don
or of Erica, among many other things
So this isn't a blue sky research at all, and I think they had Go in
crosshairs for most of the company's existence. I don't know the
details of how DeepMind operates, but I'd imagine the company works
on multiple
ital point move will have high action value".
[1] BTW, there has been a good influx of new mailing list
subscriptions in the last few days!
[2] AMAF is then a common prefix context, but let's ignore it as
AlphaGo doesn't use it.
--
Petr Baud
cky timing for Zen... Still, a treat for KGS denizens. :-)
Is this a result of adding a DCNN move classifier to the Zen MCTS as
another prior, or some other improvement?
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can d
s essentially what
> happened following Deep Blue's win against Kasperov. And now their are
> solutions on single desktops that can best what Deep Blue did with far more
> computational resources.
Certainly!
Also, reflecting on what I just wrote,
> On Thu, Jan 28, 2016 at 10
al resources applied to this, which
is of course an obstacle (except the big IT companies).
I think the next main avenue of research is exploring solutions that
are much less resource-hungry. The main problem here is hungry at
training time, not play time. Well,
play Go anymore. And none of these facts are causally
connected in any way AFAIK!)
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
C
out that if Pachi decides it's losing, the gameplay
is switched over to GNUGo to finish the game.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
ist owner and pays the bills for computer-go.org; I do most of
the day-to-day (well, month-to-month) administration and moderation.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
PUs and very high thinking time, this
> could be the way.
>
> Josef
>
> On Tue, Dec 8, 2015 at 5:17 PM Petr Baudis wrote:
>
> > Hi!
> >
> > In case someone is looking for a starting point to actually implement
> > Go rules etc. on GPU, you may fin
;getForthLastMove().getPosition(),size);
> > data[12*size*size+size*j+k]=1.0;
> > }
> > }
> >
> > -BEGIN PGP SIGNATURE-
> > Version: GnuPG v2.0.22 (GNU/Linux)
> >
> > iQIcBAEBAgAGBQJWZvOlAAoJEInWdHg+Znf4t8cP/2a9fE7rVb3Hz9wvdMkvVkFS
> >
onger"
and better encompassing the board situation. This should result in
better one-move predictions in a situation where the followup is also
important.
It sounds rather reasonable to me...?
--
Petr Baudis
If you have good ideas, good data and fast compute
oven / reproduced) or just (thoroughly) investigated
by a human.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
On Tue, Nov 24, 2015 at 01:39:00PM +0100, Petr Baudis wrote:
> On Mon, Nov 23, 2015 at 10:00:27PM -0800, David Fotland wrote:
> > 1 kyu on KGS with no search is pretty impressive.
>
> But it doesn't correlate very well with the reported results against
> Pachi, it seems
are necessarily complete games. But they are all
played against a fixed opponent, MCTS program.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
X8350.)
> Perhaps Darkforest2 is too slow.
Darkfores2 should be just different parameters when training the
network, according to the paper if I understood it right.
Petr Baudis
___
Computer-go mailing list
Computer-go
ed bots are estimated at 4k-5k level based on performance against
> other machine players. Adding MCTS to darkforest creates a much stronger
> player: with only 1000 rollouts, darkforest+MCTS beats pure darkforest 90%
> of the time; with 5000 rollouts, our best model plus MCTS beats Pachi wit
n/loss. You might try to see what happens
if, in addition to maximize_score, you also pass
val_scale=0.1
(instead of the default 0.01) or even larger value. Not sure what
effect on strength it might have.
Petr Baudis
__
r scheme might be to drop, say, a block of 20 moves
starting at move 40-80 at random.)
I think a good question is what other uses besides learning move
patterns do people envision.
--
Petr Baudis
If you have good ideas, good data and fast computers,
copyright protection.
> 2a) Size: My current view is that at least 2 sizes are necessary: small
> (1000-2000 games?) and large dataset (5-6 games).
What's the usecase for a small dataset?
--
Petr Baudis
If you have good ideas, good d
would be
a lot easier with proper tools to analyze "aggregate" behavior near the
leaves. (But this is just my personal hypothesis.)
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hin
ds on playing style as much as anything. But
others in this thread made my argument better.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
s.
I find the notion above really counterintuitive, personally.
Do you have any statistical evidence for this? I.e. increasing portions
of white wins in even games as the player rating decreases?
Petr Baudis
___
Comput
x27;s presented triggers my hype alerts, but nevertheless:
does anyone know any details about this? Most interestingly, how
strong is it?
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey H
t "round"
numbers of playouts, etc. I hope it's not a grave sin.)
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
you step through a bunch of MC simulations, you may notice that
often a large+strong group gets captured because of something silly and
then totally unrelated moves appear in the freed up space. Playing
under the stones is thus a strong indicator that we are in the "nonsense
endgame"
that) are relatively rare in Go, plus there are
pitfalls when propagating updates, aren't there? OTOH having
a fixed-size list of followups carries some overhead when the board is
getting filled up. So I never bothered to do this; but I know that some
other strong programs do use transposi
s been derived by David Silver as follows
(miraculously hosted by Hiroshi-san):
http://www.yss-aya.com/rave.pdf
Also note that RAVE_EQUIV (q_{ur} * (1-q_{ur}) / b_r^2) varies widely
among programs, IIRC; 3500 might be on the higher end of the spectrum,
it makes the transition from AMAF t
re's plenty of fast open source stuff out there.
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
ots.
Maybe you are doing it in Python? Michi's heavy playouts (also not
probability distribution) are about 15 per second per thread on 13x13.
--
Petr Baudis
If you have good ideas, good data and fast comp
On Fri, Oct 09, 2015 at 12:22:36PM +0800, Cai Gengyang wrote:
> I just defeated Hirabot12(2d) by resignation. This bot is not very strong,
> prone to making huge calculation errors in life-and-death situations ..
Which bot isn't? :-)
t propose relaxing the requirement even further, from one
desktop cpu to just one cpu - as in physical package. Many cloud
providers might give you a Xeon instance that's about as good as
a regular i7. You mainly want to exclude dedicated multi-CPU servers
and clusters.)
--
of *any* kind), that demonstrates interest
(and consequently value) to both the original poster (encouraging
further posts) and moderators.
Kind regards,
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.o
getting more and more unpleasant.)
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
to the
way you pick situations to simulate to make things work.
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mai
Hi!
On Thu, Jul 30, 2015 at 10:44:36AM +0200, Petr Baudis wrote:
> From 12:30, a match of Ingo's human-computer team (w/ CrazyStone) vs.
> a professional.
Unfortunately, the transmission of this event did not work out that
well - we hoped to show mainly the CrazyStone screen with
Hi!
On Tue, Jul 28, 2015 at 03:35:10PM +0200, remi.cou...@free.fr wrote:
> https://github.com/pasky/iggsc2015proc
On Wed, Jul 29, 2015 at 08:21:00PM +0200, Petr Baudis wrote:
> There are several Computer Go events on EGC2015.
Today, we have several IGGSC2015 events, all of them w
e enjoying it!
On Wed, Jul 29, 2015 at 09:14:14PM +0200, Rémi Coulom wrote:
> Great! Thanks. 5 stones against Aya is brave.
>
> On 07/29/2015 08:21 PM, Petr Baudis wrote:
> > Hi!
> >
> > There are several Computer Go events on EGC2015. There was a small
> >tour
a 6d:
https://www.youtube.com/watch?v=_3Lk1qVoiYM
Right now, Hajin Lee 3p (known for her live commentaries on Youtube
as "Haylee") is playing Aya (giving 5 stones) and commenting live:
https://www.youtube.com/watch?v=Ka2ilmu7Eo4
--
1 - 100 of 349 matches
Mail list logo
