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
> > >___
dition", 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 forward!
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! Fly before you crawl
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 thought
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,
--
Petr Baudis, Rossum
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 <pa...@ucw.cz> wrote:
>
> > Few open questions I currently have, comments welcome:
> >
> > - there is no input representing the number of capture
, 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 mess ri
?
>
> Álvaro.
>
>
>
> On Thu, Oct 19, 2017 at 6:17 AM, Petr Baudis <pa...@ucw.cz> 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 mo
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://computer-go.or
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
hy'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 fail really hugely. -- Moist von Lipwig
__
/computer-go.org/mailman/listinfo/computer-go
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
--
Petr Baudis, Rossum
Run before you walk! Fly before you crawl!
.
--
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
Computer-go
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 really hugely. -- Moist von Lipwig
_
; 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
meai 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
er=zen19k
>
> 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
_
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
___
Computer-go mailing li
will use this library.
> >
> >
> > Darren
> >
> > ___
> > Computer-go mailing list
> > Computer-go@computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
> >
> _
sh-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
more even,
sn'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,
you can do almost anything. -- Geoffr
ith 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://compute
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/listinfo
ivisions might not end up well.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
gt; 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
--
board_game
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
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.
>
> The record's stuck, the record's stuck.
> ___
e game 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
erties 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
ot 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.)
--
impler, 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 have good ideas, good data and f
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 graph.
--
Petr Baud
-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 d
gnificantly
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!
--
Petr Baudis
If you ha
> > 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://
new things! :)
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
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
___
Comput
: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 GMT+
s, “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
_
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
___
Computer-go mailing
11.1.
> >
> > 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
xperience,
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
__
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 research d
tones:
> 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 ideas, good data and
et...
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.
--
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.com/game
Hi!
On Mon, Feb 01, 2016 at 01:38:28PM +, Aja Huang wrote:
> On Mon, Feb 1, 2016 at 11:38 AM, Petr Baudis <pa...@ucw.cz> wrote:
> >
> > That's right, but unless I've overlooked something, I didn't see Fan Hui
> > create any complicated fight, there wasn't any
impler
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't you?
ue 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 things at once. :-)
--
Petr Baudis
ve 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 Baudis
If you have go
. :-)
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 do almost anything. -- Geoffrey Hinton
(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, the strength of this NN running on
a normal single-GPU machi
entially 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 10:07
more. 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
___
Computer-go mailing l
f 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
wner 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
URE-
> > Version: GnuPG v2.0.22 (GNU/Linux)
> >
> > iQIcBAEBAgAGBQJWZvOlAAoJEInWdHg+Znf4t8cP/2a9fE7rVb3Hz9wvdMkvVkFS
> > 4Y3AomVx8i56jexVyXuzKihfizVRM7x6lBiwjYBhj4Rm9UFWjj2ZvDzBGCm3Sy4I
> > SpG8D01VnzVR6iC1YTu3ecv9Wo4pTjc7NL5pAxiZDB0V7OTRklfZAYsX4mWyHygn
> > c
nd very high thinking time, this
> could be the way.
>
> Josef
>
> On Tue, Dec 8, 2015 at 5:17 PM Petr Baudis <pa...@ucw.cz> wrote:
>
> > Hi!
> >
> > In case someone is looking for a starting point to actually implement
> > Go rules etc. on
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
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 to me
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
arily 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
.)
> 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@comp
ed 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 with
> 10,000 rollouts 95.5% of the time
ou 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
___
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 data and fast co
ight 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,
yo
s than top professionals.
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
___
laying 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
ound"
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
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 Hinton
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
o, 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 transposition tables.
--
e stones?
Also, if 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
en
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
e 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 computers,
you can do
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? :-)
Petr
tes 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.org
http://computer-go.org/mail
ng 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
things work.
--
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
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
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 move rating
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
tournament of programs, played out on identical hardware
:
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
--
Petr Baudis
Benson life algorithm and some simple heuristics to determine
life and death. (optional)
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
are
not fatal, so my workaround is to use kgsGtp-3.5.4 for now. What did
others do?
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
reasonably nice hardware, the games will be played on KGS and we
can arrange on-site operators for a limited number of developers who
cannot attend in person. Unfortunately, only single (1) participant
has registered so far...
On Tue, Jun 16, 2015 at 12:07:17PM +0200, Petr Baudis wrote:
On Mon, Jun 15
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
game, so participants
wouldn't miss that. However, of course there will some other things
to do on that day like side tournaments or trips. :-)
--
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything
Hello!
This is a reminder that the deadline for paper submission for the
IGGSC 2015 at the European Go Congress is in two weeks.
Call for Papers - Second International Go Game Science Conference
=
Liberec, Czech Republic,
with it at this point (now I just
hoped to try to pair it up with other opponents) but maybe others will
make use of it.
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman
On Sun, Apr 26, 2015 at 11:26:42PM +0200, Petr Baudis wrote:
On Sun, Apr 26, 2015 at 12:17:01PM +0200, remi.cou...@free.fr wrote:
Hi,
I thought it might be fun to have a tournament on a very large board. It
might also motivate research into more clever adaptive playouts. Maybe a
KGS
, not part of MCTS. Is it possible to run oakfoam's DCNN
implementation like that? (Have you measured its stength?)
Thanks,
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman
...
Petr Baudis
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go
, Hideki Kato wrote:
For prior values in the tree, almost(?) all strong programs use Remi's
method these days.
http://remi.coulom.free.fr/Amsterdam2007/MMGoPatterns.pdf
Do you mean all the strong programs do progressive widening?
--
Petr Baudis
If you
1 - 100 of 309 matches
Mail list logo