Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-09 Thread Rémi Coulom 
The two wins of King against Kata have the same opening.

I made the opening book of Crazy Stone to avoid this problem. Whenever it
draws or loses a game, it marks the leaf of the tree as losing, so that it
avoids playing it again.

On Sat, May 9, 2020 at 5:06 AM David Wu  wrote:

> On Fri, May 8, 2020 at 8:46 PM uurtamo .  wrote:
>
>> And this has no book, right? So it should be badly abused by a very good
>> book?
>>
>>
> Maybe!
>
> But the version that was running before which went something like 48-52-1
> (last time I counted it up) against the other top 3 bots that were rated
> 3300+ also had no book. Granted, the newer one is coded to play a
> little more excitingly on average, probably so its opening lines might have
> more flaws. At least, that's what the net should have been trained to do.
> (katab40s37-pda1)
>
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-08 Thread David Wu 
On Fri, May 8, 2020 at 8:46 PM uurtamo .  wrote:

> And this has no book, right? So it should be badly abused by a very good
> book?
>
>
Maybe!

But the version that was running before which went something like 48-52-1
(last time I counted it up) against the other top 3 bots that were rated
3300+ also had no book. Granted, the newer one is coded to play a
little more excitingly on average, probably so its opening lines might have
more flaws. At least, that's what the net should have been trained to do.
(katab40s37-pda1)
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-08 Thread David Wu 
kata-bot on OGS is intended for human players on OGS and is never
guaranteed to be any particular version (certainly not an up-to-date
version) nor have any specific fixed settings. You should generally not use
it for testing - just download KataGo and run it yourself (in Lizzie, or
Sabaki, or whatever) if you want reliable settings.

The "aggressive" version that I mentioned in my last email is running on
cgos, not on OGS.

On Fri, May 8, 2020 at 8:23 PM Kyle Biedermann 
wrote:

> Sounds fun and interesting experiment, I have noticed the increase in
> preference to the 4-4 as of lately across the majority of AI. I still
> prefer the 5-5 opening it seems to hold against Katago at the moment. Maybe
> i'll test out some things to see if it can find some interesting new moves.
> Is it still the Kata-bot account on OGS?.
>
> Kyle Biedermann
> Creator of Deep Scholar
>
> On Fri, May 8, 2020 at 3:28 PM David Wu  wrote:
>
>> I'm running a new account of KataGo that is set to bias towards
>> aggressive or difficult moves now (the same way it does in 19x19 handicap
>> games), to see what the effect is. Although, it seems like some people have
>> stopped running their bots.  Still maybe it will be interesting for the
>> remaining players, or any others who decide to re-turn-on their bot for a
>> little while. :)
>>
>> It seems like some fraction of the time, it now opens on 5-5 as black,
>> which is judged as worse than 4-4 in an even game, but presumably is more
>> difficult to play. I suspect it will now start to lose a noticeable number
>> of games now due to overplaying, and there's a good chance it does much
>> worse overall. Even so, I'm curious what will happen, and what the draw
>> rate will be. Suddenly having some 5-5 openings should certainly add some
>> variety to the games.
>>
>> On Thu, May 7, 2020 at 12:41 PM David Wu  wrote:
>>
>>> Having it matter which of the stones you capture there is fascinating.
>>> Thanks for the analysis - and thanks for "organizing" this 9x9 testing
>>> party. :)
>>>
>>> On Thu, May 7, 2020 at 12:06 PM Rémi Coulom 
>>> wrote:
>>>
 If White recaptures the Ko, then Black can play at White's 56, capture
 the stone, and win by 2 points.

 On Thu, May 7, 2020 at 5:02 PM Shawn Ligocki 
 wrote:

> Thanks for sharing the games, Rémi!
>
> On Thu, May 7, 2020 at 6:27 AM Rémi Coulom 
> wrote:
>
>> In this game, Crazy Stone won using a typical Monte Carlo trick:
>> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
>> On move 27, it sacrificed a stone. According to Crazy Stone, the game
>> would have been a draw had Aya just re-captured it. But Aya took the bait
>> and captured the other stone. Crazy Stone's evaluation became instantly
>> winning after this, the sacrificed stone serving as a threat for the
>> winning ko fight, 18 moves later.
>>
>
> Wow, I did not imagine how that move would be useful later! But the
> very end is confusing to my human brain, couldn't White move 56 retake the
> ko and win it? It seems like Black only has one real ko threat left (J4
> maybe). But White also has one huge threat left (D3), so it seems like
> White should win this ko and then be about 4 ahead with komi. Am I
> missing something?
>
> -Shawn
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
 ___
 Computer-go mailing list
 [email protected]
 http://computer-go.org/mailman/listinfo/computer-go

>>> ___
>> Computer-go mailing list
>> [email protected]
>> http://computer-go.org/mailman/listinfo/computer-go
>>
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-08 Thread uurtamo . 
And this has no book, right? So it should be badly abused by a very good
book?

s.

On Fri, May 8, 2020, 3:28 PM David Wu  wrote:

> I'm running a new account of KataGo that is set to bias towards aggressive
> or difficult moves now (the same way it does in 19x19 handicap games), to
> see what the effect is. Although, it seems like some people have stopped
> running their bots.  Still maybe it will be interesting for the
> remaining players, or any others who decide to re-turn-on their bot for a
> little while. :)
>
> It seems like some fraction of the time, it now opens on 5-5 as black,
> which is judged as worse than 4-4 in an even game, but presumably is more
> difficult to play. I suspect it will now start to lose a noticeable number
> of games now due to overplaying, and there's a good chance it does much
> worse overall. Even so, I'm curious what will happen, and what the draw
> rate will be. Suddenly having some 5-5 openings should certainly add some
> variety to the games.
>
> On Thu, May 7, 2020 at 12:41 PM David Wu  wrote:
>
>> Having it matter which of the stones you capture there is fascinating.
>> Thanks for the analysis - and thanks for "organizing" this 9x9 testing
>> party. :)
>>
>> On Thu, May 7, 2020 at 12:06 PM Rémi Coulom 
>> wrote:
>>
>>> If White recaptures the Ko, then Black can play at White's 56, capture
>>> the stone, and win by 2 points.
>>>
>>> On Thu, May 7, 2020 at 5:02 PM Shawn Ligocki  wrote:
>>>
 Thanks for sharing the games, Rémi!

 On Thu, May 7, 2020 at 6:27 AM Rémi Coulom 
 wrote:

> In this game, Crazy Stone won using a typical Monte Carlo trick:
> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
> On move 27, it sacrificed a stone. According to Crazy Stone, the game
> would have been a draw had Aya just re-captured it. But Aya took the bait
> and captured the other stone. Crazy Stone's evaluation became instantly
> winning after this, the sacrificed stone serving as a threat for the
> winning ko fight, 18 moves later.
>

 Wow, I did not imagine how that move would be useful later! But the
 very end is confusing to my human brain, couldn't White move 56 retake the
 ko and win it? It seems like Black only has one real ko threat left (J4
 maybe). But White also has one huge threat left (D3), so it seems like
 White should win this ko and then be about 4 ahead with komi. Am I
 missing something?

 -Shawn
 ___
 Computer-go mailing list
 [email protected]
 http://computer-go.org/mailman/listinfo/computer-go

>>> ___
>>> Computer-go mailing list
>>> [email protected]
>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-08 Thread Kyle Biedermann 
Sounds fun and interesting experiment, I have noticed the increase in
preference to the 4-4 as of lately across the majority of AI. I still
prefer the 5-5 opening it seems to hold against Katago at the moment. Maybe
i'll test out some things to see if it can find some interesting new moves.
Is it still the Kata-bot account on OGS?.

Kyle Biedermann
Creator of Deep Scholar

On Fri, May 8, 2020 at 3:28 PM David Wu  wrote:

> I'm running a new account of KataGo that is set to bias towards aggressive
> or difficult moves now (the same way it does in 19x19 handicap games), to
> see what the effect is. Although, it seems like some people have stopped
> running their bots.  Still maybe it will be interesting for the
> remaining players, or any others who decide to re-turn-on their bot for a
> little while. :)
>
> It seems like some fraction of the time, it now opens on 5-5 as black,
> which is judged as worse than 4-4 in an even game, but presumably is more
> difficult to play. I suspect it will now start to lose a noticeable number
> of games now due to overplaying, and there's a good chance it does much
> worse overall. Even so, I'm curious what will happen, and what the draw
> rate will be. Suddenly having some 5-5 openings should certainly add some
> variety to the games.
>
> On Thu, May 7, 2020 at 12:41 PM David Wu  wrote:
>
>> Having it matter which of the stones you capture there is fascinating.
>> Thanks for the analysis - and thanks for "organizing" this 9x9 testing
>> party. :)
>>
>> On Thu, May 7, 2020 at 12:06 PM Rémi Coulom 
>> wrote:
>>
>>> If White recaptures the Ko, then Black can play at White's 56, capture
>>> the stone, and win by 2 points.
>>>
>>> On Thu, May 7, 2020 at 5:02 PM Shawn Ligocki  wrote:
>>>
 Thanks for sharing the games, Rémi!

 On Thu, May 7, 2020 at 6:27 AM Rémi Coulom 
 wrote:

> In this game, Crazy Stone won using a typical Monte Carlo trick:
> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
> On move 27, it sacrificed a stone. According to Crazy Stone, the game
> would have been a draw had Aya just re-captured it. But Aya took the bait
> and captured the other stone. Crazy Stone's evaluation became instantly
> winning after this, the sacrificed stone serving as a threat for the
> winning ko fight, 18 moves later.
>

 Wow, I did not imagine how that move would be useful later! But the
 very end is confusing to my human brain, couldn't White move 56 retake the
 ko and win it? It seems like Black only has one real ko threat left (J4
 maybe). But White also has one huge threat left (D3), so it seems like
 White should win this ko and then be about 4 ahead with komi. Am I
 missing something?

 -Shawn
 ___
 Computer-go mailing list
 [email protected]
 http://computer-go.org/mailman/listinfo/computer-go

>>> ___
>>> Computer-go mailing list
>>> [email protected]
>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-08 Thread David Wu 
I'm running a new account of KataGo that is set to bias towards aggressive
or difficult moves now (the same way it does in 19x19 handicap games), to
see what the effect is. Although, it seems like some people have stopped
running their bots.  Still maybe it will be interesting for the
remaining players, or any others who decide to re-turn-on their bot for a
little while. :)

It seems like some fraction of the time, it now opens on 5-5 as black,
which is judged as worse than 4-4 in an even game, but presumably is more
difficult to play. I suspect it will now start to lose a noticeable number
of games now due to overplaying, and there's a good chance it does much
worse overall. Even so, I'm curious what will happen, and what the draw
rate will be. Suddenly having some 5-5 openings should certainly add some
variety to the games.

On Thu, May 7, 2020 at 12:41 PM David Wu  wrote:

> Having it matter which of the stones you capture there is fascinating.
> Thanks for the analysis - and thanks for "organizing" this 9x9 testing
> party. :)
>
> On Thu, May 7, 2020 at 12:06 PM Rémi Coulom  wrote:
>
>> If White recaptures the Ko, then Black can play at White's 56, capture
>> the stone, and win by 2 points.
>>
>> On Thu, May 7, 2020 at 5:02 PM Shawn Ligocki  wrote:
>>
>>> Thanks for sharing the games, Rémi!
>>>
>>> On Thu, May 7, 2020 at 6:27 AM Rémi Coulom 
>>> wrote:
>>>
 In this game, Crazy Stone won using a typical Monte Carlo trick:
 http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
 On move 27, it sacrificed a stone. According to Crazy Stone, the game
 would have been a draw had Aya just re-captured it. But Aya took the bait
 and captured the other stone. Crazy Stone's evaluation became instantly
 winning after this, the sacrificed stone serving as a threat for the
 winning ko fight, 18 moves later.

>>>
>>> Wow, I did not imagine how that move would be useful later! But the very
>>> end is confusing to my human brain, couldn't White move 56 retake the ko
>>> and win it? It seems like Black only has one real ko threat left (J4
>>> maybe). But White also has one huge threat left (D3), so it seems like
>>> White should win this ko and then be about 4 ahead with komi. Am I
>>> missing something?
>>>
>>> -Shawn
>>> ___
>>> Computer-go mailing list
>>> [email protected]
>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>> ___
>> Computer-go mailing list
>> [email protected]
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-08 Thread Kyle Biedermann 
I looked through the game on one point I found some draw lines at move 13
b5 instead of b6 I tried out the line on OGS against KataGo
https://online-go.com/game/23768001 small sample if you have any other
variations you want me to try out I could do that.

Kyle Biedermann
Creator of Deep Scholar

On Fri, May 8, 2020 at 1:29 AM Kensuke Matsuzaki 
wrote:

> Rn says move 21 and move 27 was not good, but I can't understand.
> rn.6.3.945 is running on EC2 g4dn.12xlarge, and it's network is 256
> channel * 20 resnet blocks.
>
> > And congratulations to rn for beating kata in a very beautiful game:
> > http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/08/998312.sgf
> >
> > I am not strong enough to appreciate all the subtleties, but the
> complexity looks amazing.
> --
> Kensuke Matsuzaki
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-08 Thread Kensuke Matsuzaki 
Rn says move 21 and move 27 was not good, but I can't understand.
rn.6.3.945 is running on EC2 g4dn.12xlarge, and it's network is 256
channel * 20 resnet blocks.

> And congratulations to rn for beating kata in a very beautiful game:
> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/08/998312.sgf
>
> I am not strong enough to appreciate all the subtleties, but the complexity 
> looks amazing.
--
Kensuke Matsuzaki
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread Rémi Coulom 
And congratulations to rn for beating kata in a very beautiful game:
http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/08/998312.sgf

I am not strong enough to appreciate all the subtleties, but the complexity
looks amazing.

Rémi

On Thu, May 7, 2020 at 10:04 PM Ryan Hayward  wrote:

> Hey Martin,
>
> thanks!  I never realized that the sgf came with a viewer... beautiful :)
>
> yeah, wild wild wild...
>
> looking forward to seeing 6x6 games like this :)
>
> R
>
> On Thu, May 7, 2020 at 1:03 PM Martin Mueller 
> wrote:
>
>> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997479.sgf
>>
>> Great games! This is my favorite so far. The way black lives inside the
>> super-safe white area is incredible...
>>
>> Martin
>> ___
>> Computer-go mailing list
>> [email protected]
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
>
> --
> Professor Ryan B. Hayward, Computing Science Dept., UAlberta, Edmonton T6G
> 2E8, Canada 780-492-2285  RyanBHayward
>   @RyanBHayward
>  Hex-the-full-story
> 
>
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread Ryan Hayward 
Hey Martin,

thanks!  I never realized that the sgf came with a viewer... beautiful :)

yeah, wild wild wild...

looking forward to seeing 6x6 games like this :)

R

On Thu, May 7, 2020 at 1:03 PM Martin Mueller  wrote:

> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997479.sgf
>
> Great games! This is my favorite so far. The way black lives inside the
> super-safe white area is incredible...
>
> Martin
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>


-- 
Professor Ryan B. Hayward, Computing Science Dept., UAlberta, Edmonton T6G
2E8, Canada 780-492-2285  RyanBHayward
  @RyanBHayward
 Hex-the-full-story

___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread Martin Mueller 
http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997479.sgf

Great games! This is my favorite so far. The way black lives inside the
super-safe white area is incredible...

Martin
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread David Wu 
Having it matter which of the stones you capture there is fascinating.
Thanks for the analysis - and thanks for "organizing" this 9x9 testing
party. :)

On Thu, May 7, 2020 at 12:06 PM Rémi Coulom  wrote:

> If White recaptures the Ko, then Black can play at White's 56, capture the
> stone, and win by 2 points.
>
> On Thu, May 7, 2020 at 5:02 PM Shawn Ligocki  wrote:
>
>> Thanks for sharing the games, Rémi!
>>
>> On Thu, May 7, 2020 at 6:27 AM Rémi Coulom  wrote:
>>
>>> In this game, Crazy Stone won using a typical Monte Carlo trick:
>>> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
>>> On move 27, it sacrificed a stone. According to Crazy Stone, the game
>>> would have been a draw had Aya just re-captured it. But Aya took the bait
>>> and captured the other stone. Crazy Stone's evaluation became instantly
>>> winning after this, the sacrificed stone serving as a threat for the
>>> winning ko fight, 18 moves later.
>>>
>>
>> Wow, I did not imagine how that move would be useful later! But the very
>> end is confusing to my human brain, couldn't White move 56 retake the ko
>> and win it? It seems like Black only has one real ko threat left (J4
>> maybe). But White also has one huge threat left (D3), so it seems like
>> White should win this ko and then be about 4 ahead with komi. Am I
>> missing something?
>>
>> -Shawn
>> ___
>> Computer-go mailing list
>> [email protected]
>> http://computer-go.org/mailman/listinfo/computer-go
>>
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread Rémi Coulom 
If White recaptures the Ko, then Black can play at White's 56, capture the
stone, and win by 2 points.

On Thu, May 7, 2020 at 5:02 PM Shawn Ligocki  wrote:

> Thanks for sharing the games, Rémi!
>
> On Thu, May 7, 2020 at 6:27 AM Rémi Coulom  wrote:
>
>> In this game, Crazy Stone won using a typical Monte Carlo trick:
>> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
>> On move 27, it sacrificed a stone. According to Crazy Stone, the game
>> would have been a draw had Aya just re-captured it. But Aya took the bait
>> and captured the other stone. Crazy Stone's evaluation became instantly
>> winning after this, the sacrificed stone serving as a threat for the
>> winning ko fight, 18 moves later.
>>
>
> Wow, I did not imagine how that move would be useful later! But the very
> end is confusing to my human brain, couldn't White move 56 retake the ko
> and win it? It seems like Black only has one real ko threat left (J4
> maybe). But White also has one huge threat left (D3), so it seems like
> White should win this ko and then be about 4 ahead with komi. Am I
> missing something?
>
> -Shawn
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread David Wu 
Yes, it's fun to see suddenly a little cluster of people running strong 9x9
bots. :)

katab40s37-awsp3 is running on one AWS p3 2xlarge instance. So it's a
single V100, with some settings tuned appropriately for good performance on
that hardware and board size and time control (mainly, 96 threads), and
also some of the score maximization config settings toned down so as to
focus more on win/loss. It's running one of the most recent 40 block KataGo
nets from the current ongoing training run, a net that isn't released yet
but which I'll release soon. But it's only more recent by a couple of
weeks, the latest released ones should probably be about the same strength
too.

I think it gets somewhere from 5000 to 7000 playouts per second, I forget
what the exact numbers were. No opening book, just searching from scratch.
A book seems like it would enable a large increase in the effective number
of playouts early on (and save time for deeper search out-of-book too), but
I haven't worked on book code.

The current run, which has been ongoing for a few months on variously from
37 to 47 V100s spends about 4% of its games on 9x9, which probably amounts
to 1%-2% of the total compute since 9x9 games are much shorter than games
on larger boards. So presumably a lot of the strength on 9x9 is due to the
neural net generalizing its knowledge from other board sizes, since the
same net trains on all sizes at the same time.

There's a setting in KataGo ("PDA") that causes it to play a bit more
aggressively, in whatever way it has learned from self-play that increases
the likelihood of weaker players making a mistake. In 19x19 handicap games,
it gives a strong boost in how many handicap stones it's capable of
offering to weaker opponents, even helping against players near human pro
level. I haven't turned it on here, but maybe I could make a second
username with this set to a nonzero value. I'd be curious if it would make
KataGo avoid some of the more easily drawn lines of play in favor of ones
that would be more challenging for most opponents.


On Thu, May 7, 2020 at 6:27 AM Rémi Coulom  wrote:

> Hi,
>
> Thanks to all the strong bots who joined. Kata is impressive. Does anyone
> know more about its configuration? Is it a single V100 or many?
>
> I watched some games, and some where spectacular.
>
> A firework of ko fights:
> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997314.sgf
>
> In this game, Crazy Stone won using a typical Monte Carlo trick:
> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
> On move 27, it sacrificed a stone. According to Crazy Stone, the game
> would have been a draw had Aya just re-captured it. But Aya took the bait
> and captured the other stone. Crazy Stone's evaluation became instantly
> winning after this, the sacrificed stone serving as a threat for the
> winning ko fight, 18 moves later.
>
> Rémi
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread Shawn Ligocki 
Thanks for sharing the games, Rémi!

On Thu, May 7, 2020 at 6:27 AM Rémi Coulom  wrote:

> In this game, Crazy Stone won using a typical Monte Carlo trick:
> http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
> On move 27, it sacrificed a stone. According to Crazy Stone, the game
> would have been a draw had Aya just re-captured it. But Aya took the bait
> and captured the other stone. Crazy Stone's evaluation became instantly
> winning after this, the sacrificed stone serving as a threat for the
> winning ko fight, 18 moves later.
>

Wow, I did not imagine how that move would be useful later! But the very
end is confusing to my human brain, couldn't White move 56 retake the ko
and win it? It seems like Black only has one real ko threat left (J4
maybe). But White also has one huge threat left (D3), so it seems like
White should win this ko and then be about 4 ahead with komi. Am I
missing something?

-Shawn
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-07 Thread Rémi Coulom 
Hi,

Thanks to all the strong bots who joined. Kata is impressive. Does anyone
know more about its configuration? Is it a single V100 or many?

I watched some games, and some where spectacular.

A firework of ko fights:
http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997314.sgf

In this game, Crazy Stone won using a typical Monte Carlo trick:
http://www.yss-aya.com/cgos/viewer.cgi?9x9/SGF/2020/05/07/997390.sgf
On move 27, it sacrificed a stone. According to Crazy Stone, the game would
have been a draw had Aya just re-captured it. But Aya took the bait and
captured the other stone. Crazy Stone's evaluation became instantly winning
after this, the sacrificed stone serving as a threat for the winning ko
fight, 18 moves later.

Rémi
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-06 Thread Brian Lee 
Agreed on the book interface!

If you click through to the end of a variation, you can see that the
evaluation is a minimax'd evaluation, instead of an average over the
subtree nodes, even if the overall tree was generated via a UCT algorithm.
The values seem a bit more fragile to me as a result...

On Wed, May 6, 2020 at 2:25 PM uurtamo .  wrote:

> great book interface, by the way.
>
> s.
>
>
> On Wed, May 6, 2020 at 11:01 AM Rémi Coulom  wrote:
>
>> Hi,
>>
>> I trained a neural network for 9x9, and it is playing on CGOS.
>>
>> The network has 40 layers (20 residual blocks) of 256 units. It is
>> running on a Titan V GPU, with a batch of 64, at about 9k playouts per
>> second.
>>
>> It is using an opening book that you can browse online there:
>> https://www.crazy-sensei.com/book/go_9x9/
>> Each node of the book was searched with 400k playouts.
>>
>> I will let it play for a few days.
>>
>> Rémi
>> ___
>> Computer-go mailing list
>> [email protected]
>> http://computer-go.org/mailman/listinfo/computer-go
>>
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Crazy Stone is playing on CGOS 9x9

2020-05-06 Thread uurtamo . 
great book interface, by the way.

s.


On Wed, May 6, 2020 at 11:01 AM Rémi Coulom  wrote:

> Hi,
>
> I trained a neural network for 9x9, and it is playing on CGOS.
>
> The network has 40 layers (20 residual blocks) of 256 units. It is running
> on a Titan V GPU, with a batch of 64, at about 9k playouts per second.
>
> It is using an opening book that you can browse online there:
> https://www.crazy-sensei.com/book/go_9x9/
> Each node of the book was searched with 400k playouts.
>
> I will let it play for a few days.
>
> Rémi
> ___
> Computer-go mailing list
> [email protected]
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go