Re: [Computer-go] Reminder: Handicap-29 Prize

[fotland]

That's easy enough. Mfog12 trial is a free download and I can provide a 
registration code for the computer used for any competition to enable the 12 
kyu level.  12 kyu has not full board search, monte carlo or otherwise.

David

-Original Message-
From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
"Ingo Althöfer"
Sent: Thursday, January 5, 2017 3:31 AM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] Reminder: Handicap-29 Prize

Hi,

a few years ago we had agreed that for winning the bet it would be sufficient 
to beat the non-deterministic 12-kyu level of MFoG 11 (or MFoG 12). This level 
has no Monte Carlo elements ionvolved.

Ingo.
 
 

Gesendet: Donnerstag, 05. Januar 2017 um 04:15 Uhr
Von: fotl...@smart-games.com
An: computer-go@computer-go.org
Betreff: Re: [Computer-go] Reminder: Handicap-29 Prize

Yes. I’m travelling this week, but when I get home I can look for it. I’m not 
sure I can find the old source backups to make a gtp version.
 
David
 
From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Álvaro Begué
Sent: Wednesday, January 4, 2017 4:48 PM
To: computer-go 
Subject: Re: [Computer-go] Reminder: Handicap-29 Prize
 

Would you be willing to make the executable of mfgo1998 available so we can run 
it locally? Or even better, something with the same engine but which speaks GTP?

 

Álvaro.

 

 

 

 

 

On Wed, Jan 4, 2017 at 10:32 PM, "Ingo Althöfer" 
<3-hirn-ver...@gmx.de[mailto:3-hirn-ver...@gmx.de]> wrote:
Like in every year, the reminder on my Handicap-29 prize:
http://www.althofer.de/handicap-29-prize.html[http://www.althofer.de/handicap-29-prize.html]

I think, AlphaGo in its current form would not have a chance to cash in ;-)

Ingo.
___
Computer-go mailing list
Computer-go@computer-go.org[mailto: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[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/computer-go

Re: [Computer-go] it's alphago

[fotland]

Competitive with Alpha-go, one developer, not possible. I do think it is 
possible to make a pro level program with one person or a small team. Look at 
Deep Zen and Aya for example. I expect I’ll get there (pro level) with Many 
Faces as well.

 

David

 

From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Adrian Petrescu
Sent: Thursday, January 5, 2017 10:36 AM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] it's alphago

 

As an individual? Probably, yes.

 

On Thu, Jan 5, 2017 at 1:34 PM, Xavier Combelle  > wrote:



Le 05/01/2017 à 02:16, Yamato a écrit :
> Yes, it is AlphaGo. I am relieved that DeepMind clarified this.
>
> Honestly I got a little frustrated that many people didn't think that
> was AlphaGo. It was almost clear to me because I know the difficulty of
> developing AlphaGo-like bots.
thanks for this insight, if I understand well developing a bot
competitive with alphago
is nearly an impossible task?

___
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

Re: [Computer-go] ICGA Journal with new Steam

[Rémi Coulom]

Thanks to the new volunteers. I hope the new team will consider making the 
journal available online.

Rémi

- Mail original -
De: "Ingo Althöfer" <3-hirn-ver...@gmx.de>
À: computer-go@computer-go.org
Envoyé: Jeudi 5 Janvier 2017 21:32:55
Objet: [Computer-go] ICGA Journal with new Steam

Hello everybody,

as some of you know, I am Vice President of the ICGA
(= International Computer Games Association). After
a very long and successful period (over 30 years) with
Prof. Dr. Jaap van den Herik as Chief Editor, now a
new team will steer the Journal. The official statement
of the ICGA says:


With great pleasure we announce the continuation of communication 
of progress in our games community via the ICGA Journal.

All members who have paid their membership fee for 2016 can learn 
from this communication that they have paid already for the issues 
appearing in 2017. (Explanation: There were no issues of the Journal
in 2016.)

IN GENERAL

The main goal of this communication is to inform you that we have 
recently filled in the position of Editor-in-Chief of the ICGA Journal 
by an excellent researcher from Taiwan. Two new board members will 
support him and also an editorial manager will help with the daily activities.

Moreover, we have an Editor for the second part of the Journal, containing 
the Reports and Issues of General Interest, and an Editor for General ICGA 
Affairs.
For their publication the ICGA cooperates with IOS press, Amsterdam, the 
Netherlands. 

THE NEW BOARD 

Starting at January 1, 2017 
The ICGA Journal is in the hands of

Professor I-Chen Wu
Professor, Department of Computer Science, National Chiao Tung University
TEL: +886-3-5731855 FAX: +886-3-5733777 http://aigames.nctu.edu.tw/~icwu
who will act as Editor -in- Chief.

He will be seconded by 
Dr. Mark Winands 
Maastricht University 
Maastricht, the Netherlands
and 
Dr. Tristan Cazenave 
Dauphine University, France  

The Editorial Manager will be 
Tinghan Wei 
jour...@icga.org
Department of Computer Science, National Chiao Tung University.

Papers submitted to the ICGA Journal (see below) will finally go through him.
They will undergo a full peer review process, 
The IOS press will help the ICGA with their system.


The Editor for the second part of the ICGA Journal is
Professor Ingo Althoefer
Friedrich-Schiller-Universitaet Jena, Germany
Fakultaet fuer Mathematik und Informatik
Angewandte Mathematik
ingo.althoe...@uni-jena.de

The Editor for General ICGA affairs will be 
Dr. Walter Kosters
LIACS, Leiden University


NEW SUBMISSION PROCEDURE

This message also signals the start of a new procedure of submitting 
scientific papers (articles or notes) to the ICGA Journal.

New procedure for the Submission of scientific manuscripts 
Authors are requested to submit their manuscript electronically to the 
online submission system:
https://submissions.iospress.com/icga-journal/content/submit-manuscript 
Note that the manuscript should be uploaded as one file with tables and 
figures included.

Submission of material for the second part of the Journal should be directly 
sent to the Editor for the second part, Professor Ingo Althoefer.

THANK YOU 

We hope to have informed you well and look forward to a fruitful 
continuation of the ICGA Journal. We thank you for the very pleasant 
cooperation over many, many years.

SPECIAL THANKS

Jaap van den Herik is grateful to the new Editorial Board for his 
appointment as Honorary Editor. He wishes the new Board Members all 
success possible.

*

So guys, when you have interesting tournament reports, event announcements,
book reviews, or essays, feel free to send it to me. 

By the way, one of my ideas is to have a regular (or irregular, we will see)
column "best of the computer go mailing list".

The Journal appears on paper every three months, so four issues per year. 
Typically it has 64 pages in each issue,  and costs 40 Euro per year - of 
course to be paid in advance.

Ingo.
___
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

Re: [Computer-go] Are the AlphaGols coming?

[terry mcintyre]

 blockquote, div.yahoo_quoted { margin-left: 0 !important; border-left:1px 
#715FFA solid !important; padding-left:1ex !important; background-color:white 
!important; } During its training, AlphaGo played many handicap games against a 
previous version of itself, so the team and the program are acquainted with 
handicap play. I don't recall reading any discussion of komi experiments. 
Google's advantage is that they can dynamically spin up bunches of processors 
to try all sorts of experiments, including tournaments designed to test various 
versions, theories, and tweaks. There was some discussion about what to do if 
one could spin up thousands of processr cores on demand. 
There are surely large businesses in China which could do the same. They have 
similar reasons to pursue deep learning and other creative uses of big data and 
supercomputing. 


Sent from Yahoo Mail for iPad


On Thursday, January 5, 2017, 9:36 PM, David Ongaro  
wrote:This discussion reminds me of an incident which happened at the EGC in 
Tuchola 2004 (maybe someone can find a source for this). I don’t remember all 
details but it was about like this:


Two amateur players where analyzing a Game and a professional player happened 
to come by. So they asked him how he would assess the position. After a quick 
look he said “White is leading by two points”. The two players where wondering: 
“You can count that quickly?”, but the pro answered “No, I just asked myself if 
I would like to have black in this position. The answer is no. But with two 
extra Komi for Black it would feel ok.”
So it seems professionals already acquired some kind of “value network” due to 
their hard training, but they also can modify its assessments by taking Komi 
into account. Maybe that's something we also should do, i.e. not only train the 
value network by taking go positions and results into account but also add the 
Komi as an input (the output would still be a simple win/lose result). In that 
way we don’t have to train a different network for each Komi, even though the 
problem getting enough training data for all Komi values still remains.


On Jan 5, 2017, at 11:44 AM, David Ongaro  wrote:


On Jan 5, 2017, at 2:37 AM, Detlef Schmicker  wrote:

Hi,

what makes you think the opening theory with reverse komi would be the
same as with standard komi?

I would be afraid to invest an enormous amount of time just to learn,
that you have to open differently in reverse komi games :)


Thats why I used the comparative adjective “less”. It might not be ideal, but 
still much better than changing the fundamental structure of the opening with 
an extra stone. Furthermore the effect might not as big as you think:

1. The stronger player doesn’t have to play overplays when the handicap is 
correct. If the handicap is correct and if AlphaGo “knows” that is another 
question though… Of course the weaker player might play differently (i.e. more 
safely) but at least that is something he or she can control
2. One could even argue the other way around:  we might see more sound 
(theoretically correct) moves from AlphaGo with reverse Komi. If it's seeing 
itself ahead already during the opening it might resort to slack but safe 
moves. Since it’s still winning we can be left wondering if it was actually a 
good move. But if it does an unusual looking move which it can’t be considered 
an overplay but it’s still winning in the end with reverse Komi there should be 
a real insight to gain.

Still, a reverse Komi handicap is rather big, but it might be the next best 
thing we have without retraining the value network from scratch. Furthermore 
retraining the value network will probably affect the playing style even more.

Thanks,

David O.



Am 05.01.2017 um 10:50 schrieb Paweł Morawiecki:

2017-01-04 21:07 GMT+01:00 David Ongaro :



[...]So my question is: is it possible to have reverse Komi games
by feeding the value network with reverse colors?



In the paper from Nature (subsection "Features for policy/value
network"), authors state:

*the stone colour at each intersection was represented as either
player or opponent rather than black or white. *

Then, I think the AlphaGo algorithm would be fine with a reverse
komi. Namely, a human player takes black and has 7.5 komi. The next
step is that AlphaGo gives 2 stones of handicap but keeps 7.5 komi
(normally you have 0.5).

Aja, can you confirm this?



Also having 2 stone games is not so interesting since it would
reveal less insights for even game opening Theory.



I agree with David here, most insights we would get from even
games. But we can imagine the following show. Some games are played
with a reverse komi, some games would be played with 2 stones (yet,
white keeps 7.5 komi) and eventually the main event with normal
even games to debunk our myths on the game. Wouldn't be super
exciting!?

Best regards, Paweł

Re: [Computer-go] Our Silicon Overlord

[Robert Jasiek]

On 05.01.2017 17:32, Jim O'Flaherty wrote:

I don't follow.


1) "For each arcane position reached, there would now be ample data for 
AlphaGo to train on that particular pathway." is false. See below.


2) "two strategies. The first would be to avoid the state in the first 
place." Does AlphaGo have any strategy ever? If it does, does it have 
strategies of avoiding certain types of positions?


3) "the second would be to optimize play in that particular state." If 
you mean optimise play = maximise winning probability.


But... optimising this is hard when (under positional superko) optimal 
play can be ca. 13,500,000 moves long and the tree to that is huge. Even 
TPU sampling can be lost then.


Afterwards, there is still only one position from which to train. For NN 
learning, one position is not enough and cannot replace analysis by 
mathematical proofs ALA the NN does not emulate mathematical proving.


--
robert jasiek
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Are the AlphaGols coming?

[Robert Jasiek]

On 06.01.2017 03:36, David Ongaro wrote:

Two amateur players where analyzing a Game and a professional player happened 
to come by.
So they asked him how he would assess the position. After a quick look he said 
“White is
> leading by two points”. The two players where wondering: “You can 
count that quickly?”


Usually, accurate positional judgement (not only territory but all 
aspects) takes between a few seconds and 3 minutes, depending on the 
position and provided one is familiar with the theory.


--
robert jasiek
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Are the AlphaGols coming?

[Jim O'Flaherty]

That was a quite elegant way to present the idea. Ty for sharing.

On Jan 5, 2017 8:36 PM, "David Ongaro"  wrote:

> This discussion reminds me of an incident which happened at the EGC in
> Tuchola 2004 (maybe someone can find a source for this). I don’t remember
> all details but it was about like this:
>
> Two amateur players where analyzing a Game and a professional player
> happened to come by. So they asked him how he would assess the position.
> After a quick look he said “White is leading by two points”. The two
> players where wondering: “You can count that quickly?”, but the pro
> answered “No, I just asked myself if I would like to have black in this
> position. The answer is no. But with two extra Komi for Black it would feel
> ok.”
>
> So it seems professionals already acquired some kind of “value network”
> due to their hard training, but they also can modify its assessments by
> taking Komi into account. Maybe that's something we also should do, i.e.
> not only train the value network by taking go positions and results into
> account but also add the Komi as an input (the output would still be a
> simple win/lose result). In that way we don’t have to train a different
> network for each Komi, even though the problem getting enough training data
> for all Komi values still remains.
>
>
> On Jan 5, 2017, at 11:44 AM, David Ongaro  wrote:
>
>
> On Jan 5, 2017, at 2:37 AM, Detlef Schmicker  wrote:
>
> Hi,
>
> what makes you think the opening theory with reverse komi would be the
> same as with standard komi?
>
> I would be afraid to invest an enormous amount of time just to learn,
> that you have to open differently in reverse komi games :)
>
>
> Thats why I used the comparative adjective “less”. It might not be ideal,
> but still much better than changing the fundamental structure of the
> opening with an extra stone. Furthermore the effect might not as big as you
> think:
>
> 1. The stronger player doesn’t have to play overplays when the handicap is
> correct. If the handicap is correct and if AlphaGo “knows” that is another
> question though… Of course the weaker player might play differently (i.e.
> more safely) but at least that is something he or she can control
> 2. One could even argue the other way around:  we might see more sound
> (theoretically correct) moves from AlphaGo with reverse Komi. If it's
> seeing itself ahead already during the opening it might resort to slack but
> safe moves. Since it’s still winning we can be left wondering if it was
> actually a good move. But if it does an unusual looking move which it can’t
> be considered an overplay but it’s still winning in the end with reverse
> Komi there should be a real insight to gain.
>
> Still, a reverse Komi handicap is rather big, but it might be the next
> best thing we have without retraining the value network from scratch.
> Furthermore retraining the value network will probably affect the playing
> style even more.
>
> Thanks,
>
> David O.
>
>
> Am 05.01.2017 um 10:50 schrieb Paweł Morawiecki:
>
> 2017-01-04 21:07 GMT+01:00 David Ongaro :
>
>
> [...]So my question is: is it possible to have reverse Komi games
> by feeding the value network with reverse colors?
>
>
> In the paper from Nature (subsection "Features for policy/value
> network"), authors state:
>
> *the stone colour at each intersection was represented as either
> player or opponent rather than black or white. *
>
> Then, I think the AlphaGo algorithm would be fine with a reverse
> komi. Namely, a human player takes black and has 7.5 komi. The next
> step is that AlphaGo gives 2 stones of handicap but keeps 7.5 komi
> (normally you have 0.5).
>
> Aja, can you confirm this?
>
>
> Also having 2 stone games is not so interesting since it would
> reveal less insights for even game opening Theory.
>
>
> I agree with David here, most insights we would get from even
> games. But we can imagine the following show. Some games are played
> with a reverse komi, some games would be played with 2 stones (yet,
> white keeps 7.5 komi) and eventually the main event with normal
> even games to debunk our myths on the game. Wouldn't be super
> exciting!?
>
> Best regards, Paweł
>
>
>
> ___ 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/computer-go
>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___

Re: [Computer-go] it's alphago

[Yamato]

Hello,

On 2017/01/06 3:34, Xavier Combelle wrote:
>> Honestly I got a little frustrated that many people didn't think that
>> was AlphaGo. It was almost clear to me because I know the difficulty of
>> developing AlphaGo-like bots.
> thanks for this insight, if I understand well developing a bot
> competitive with alphago is nearly an impossible task?

It depends on which version of AlphaGo.

v13: possible
v18: very hard but not impossible
v19 or later: nearly impossible

in one year, I think.

One reason of this is that DeepMind has not published improvements
since the Nature version.

Yamato
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] ICGA Journal with new Steam

[Ingo Althöfer]

Hello everybody,

as some of you know, I am Vice President of the ICGA
(= International Computer Games Association). After
a very long and successful period (over 30 years) with
Prof. Dr. Jaap van den Herik as Chief Editor, now a
new team will steer the Journal. The official statement
of the ICGA says:


With great pleasure we announce the continuation of communication 
of progress in our games community via the ICGA Journal.

All members who have paid their membership fee for 2016 can learn 
from this communication that they have paid already for the issues 
appearing in 2017. (Explanation: There were no issues of the Journal
in 2016.)

IN GENERAL

The main goal of this communication is to inform you that we have 
recently filled in the position of Editor-in-Chief of the ICGA Journal 
by an excellent researcher from Taiwan. Two new board members will 
support him and also an editorial manager will help with the daily activities.

Moreover, we have an Editor for the second part of the Journal, containing 
the Reports and Issues of General Interest, and an Editor for General ICGA 
Affairs.
For their publication the ICGA cooperates with IOS press, Amsterdam, the 
Netherlands. 

THE NEW BOARD 

Starting at January 1, 2017 
The ICGA Journal is in the hands of

Professor I-Chen Wu
Professor, Department of Computer Science, National Chiao Tung University
TEL: +886-3-5731855 FAX: +886-3-5733777 http://aigames.nctu.edu.tw/~icwu
who will act as Editor -in- Chief.

He will be seconded by 
Dr. Mark Winands 
Maastricht University 
Maastricht, the Netherlands
and 
Dr. Tristan Cazenave 
Dauphine University, France  

The Editorial Manager will be 
Tinghan Wei 
jour...@icga.org
Department of Computer Science, National Chiao Tung University.

Papers submitted to the ICGA Journal (see below) will finally go through him.
They will undergo a full peer review process, 
The IOS press will help the ICGA with their system.


The Editor for the second part of the ICGA Journal is
Professor Ingo Althoefer
Friedrich-Schiller-Universitaet Jena, Germany
Fakultaet fuer Mathematik und Informatik
Angewandte Mathematik
ingo.althoe...@uni-jena.de

The Editor for General ICGA affairs will be 
Dr. Walter Kosters
LIACS, Leiden University


NEW SUBMISSION PROCEDURE

This message also signals the start of a new procedure of submitting 
scientific papers (articles or notes) to the ICGA Journal.

New procedure for the Submission of scientific manuscripts 
Authors are requested to submit their manuscript electronically to the 
online submission system:
https://submissions.iospress.com/icga-journal/content/submit-manuscript 
Note that the manuscript should be uploaded as one file with tables and 
figures included.

Submission of material for the second part of the Journal should be directly 
sent to the Editor for the second part, Professor Ingo Althoefer.

THANK YOU 

We hope to have informed you well and look forward to a fruitful 
continuation of the ICGA Journal. We thank you for the very pleasant 
cooperation over many, many years.

SPECIAL THANKS

Jaap van den Herik is grateful to the new Editorial Board for his 
appointment as Honorary Editor. He wishes the new Board Members all 
success possible.

*

So guys, when you have interesting tournament reports, event announcements,
book reviews, or essays, feel free to send it to me. 

By the way, one of my ideas is to have a regular (or irregular, we will see)
column "best of the computer go mailing list".

The Journal appears on paper every three months, so four issues per year. 
Typically it has 64 pages in each issue,  and costs 40 Euro per year - of 
course to be paid in advance.

Ingo.
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] it's alphago

[anoniem]

The sheer amount of processing power required is kinda frustrating..
Not able to use my computer for a whole month in order to train knowing
it is only 1/100th the training time AlphaGo was trained with..

Yet it is extremely satisfying to see it grow stronger and surpass oneself..

I hope at some point DeepMind, an research instute, another big company
or somebody else with acces to a big cluster will release pre-trained models
for everybody to experiment with=)

a poor poor student;-)

On 5 January 2017 at 19:48, Lukas van de Wiel 
wrote:

> It helps a lot if you have to do it as a job, as a paid researcher. I once
> tried it as a volunteer job for a company I worked for at the time, but we
> only got the basic infrastructure going, after half a year of work, with
> two people.
>
> We were trying a neural network approach, while everybody said NN was done
> for in AI go, and we had to do MCTS. We were stubborn, though. As we did
> not get paid for it, we essentially could do whatever we liked.
>
> We also both had social lives that we did not want to neglect totally, so
> we might have been able to do more, had we been more dedicated. ;-)
>
> On Thu, Jan 5, 2017 at 7:35 PM, Adrian Petrescu 
> wrote:
>
>> As an individual? Probably, yes.
>>
>> On Thu, Jan 5, 2017 at 1:34 PM, Xavier Combelle <
>> xavier.combe...@gmail.com> wrote:
>>
>>>
>>>
>>> Le 05/01/2017 à 02:16, Yamato a écrit :
>>> > Yes, it is AlphaGo. I am relieved that DeepMind clarified this.
>>> >
>>> > Honestly I got a little frustrated that many people didn't think that
>>> > was AlphaGo. It was almost clear to me because I know the difficulty of
>>> > developing AlphaGo-like bots.
>>> thanks for this insight, if I understand well developing a bot
>>> competitive with alphago
>>> is nearly an impossible task?
>>> ___
>>> 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/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Are the AlphaGols coming?

[David Ongaro]

> On Jan 5, 2017, at 2:37 AM, Detlef Schmicker  wrote:
> 
> Hi,
> 
> what makes you think the opening theory with reverse komi would be the
> same as with standard komi?
> 
> I would be afraid to invest an enormous amount of time just to learn,
> that you have to open differently in reverse komi games :)

Thats why I used the comparative adjective “less”. It might not be ideal, but 
still much better than changing the fundamental structure of the opening with 
an extra stone. Furthermore the effect might not as big as you think:

1. The stronger player doesn’t have to play overplays when the handicap is 
correct. If the handicap is correct and if AlphaGo “knows” that is another 
question though… Of course the weaker player might play differently (i.e. more 
safely) but at least that is something he or she can control
2. One could even argue the other way around:  we might see more sound 
(theoretically correct) moves from AlphaGo with reverse Komi. If it's seeing 
itself ahead already during the opening it might resort to slack but safe 
moves. Since it’s still winning we can be left wondering if it was actually a 
good move. But if it does an unusual looking move which it can’t be considered 
an overplay but it’s still winning in the end with reverse Komi there should be 
a real insight to gain.

Still, a reverse Komi handicap is rather big, but it might be the next best 
thing we have without retraining the value network from scratch. Furthermore 
retraining the value network will probably affect the playing style even more.

Thanks,

David O.


> Am 05.01.2017 um 10:50 schrieb Paweł Morawiecki:
>> 2017-01-04 21:07 GMT+01:00 David Ongaro :
>> 
>>> 
>>> [...]So my question is: is it possible to have reverse Komi games
>>> by feeding the value network with reverse colors?
>>> 
>> 
>> In the paper from Nature (subsection "Features for policy/value
>> network"), authors state:
>> 
>> *the stone colour at each intersection was represented as either
>> player or opponent rather than black or white. *
>> 
>> Then, I think the AlphaGo algorithm would be fine with a reverse
>> komi. Namely, a human player takes black and has 7.5 komi. The next
>> step is that AlphaGo gives 2 stones of handicap but keeps 7.5 komi
>> (normally you have 0.5).
>> 
>> Aja, can you confirm this?
>> 
>> 
>>> Also having 2 stone games is not so interesting since it would
>>> reveal less insights for even game opening Theory.
>>> 
>> 
>> I agree with David here, most insights we would get from even
>> games. But we can imagine the following show. Some games are played
>> with a reverse komi, some games would be played with 2 stones (yet,
>> white keeps 7.5 komi) and eventually the main event with normal
>> even games to debunk our myths on the game. Wouldn't be super
>> exciting!?
>> 
>> Best regards, Paweł
>> 
>> 
>> 
>> ___ 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/computer-go

Re: [Computer-go] it's alphago

[Xavier Combelle]

I mean as a company too, until this point none has succeed


Le 05/01/2017 à 19:35, Adrian Petrescu a écrit :
> As an individual? Probably, yes.
>
> On Thu, Jan 5, 2017 at 1:34 PM, Xavier Combelle
> > wrote:
>
>
>
> Le 05/01/2017 à 02:16, Yamato a écrit :
> > Yes, it is AlphaGo. I am relieved that DeepMind clarified this.
> >
> > Honestly I got a little frustrated that many people didn't think
> that
> > was AlphaGo. It was almost clear to me because I know the
> difficulty of
> > developing AlphaGo-like bots.
> thanks for this insight, if I understand well developing a bot
> competitive with alphago
> is nearly an impossible task?
> ___
> 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/computer-go

Re: [Computer-go] it's alphago

[Lukas van de Wiel]

It helps a lot if you have to do it as a job, as a paid researcher. I once
tried it as a volunteer job for a company I worked for at the time, but we
only got the basic infrastructure going, after half a year of work, with
two people.

We were trying a neural network approach, while everybody said NN was done
for in AI go, and we had to do MCTS. We were stubborn, though. As we did
not get paid for it, we essentially could do whatever we liked.

We also both had social lives that we did not want to neglect totally, so
we might have been able to do more, had we been more dedicated. ;-)

On Thu, Jan 5, 2017 at 7:35 PM, Adrian Petrescu  wrote:

> As an individual? Probably, yes.
>
> On Thu, Jan 5, 2017 at 1:34 PM, Xavier Combelle  > wrote:
>
>>
>>
>> Le 05/01/2017 à 02:16, Yamato a écrit :
>> > Yes, it is AlphaGo. I am relieved that DeepMind clarified this.
>> >
>> > Honestly I got a little frustrated that many people didn't think that
>> > was AlphaGo. It was almost clear to me because I know the difficulty of
>> > developing AlphaGo-like bots.
>> thanks for this insight, if I understand well developing a bot
>> competitive with alphago
>> is nearly an impossible task?
>> ___
>> 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/computer-go

Re: [Computer-go] it's alphago

[Xavier Combelle]

Le 05/01/2017 à 02:16, Yamato a écrit :
> Yes, it is AlphaGo. I am relieved that DeepMind clarified this.
>
> Honestly I got a little frustrated that many people didn't think that
> was AlphaGo. It was almost clear to me because I know the difficulty of
> developing AlphaGo-like bots.
thanks for this insight, if I understand well developing a bot
competitive with alphago
is nearly an impossible task?
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] it's alphago

[terry mcintyre]

It's one thing to know the recipe; it's another to have an industrial-size 
kitchen. Google was able to throw truly gargantuan amounts of computing 
resources at this problem. 

A few years back, a researcher - was it  Remi Coulon? - was able to scrounge a 
few thousand cores for a tournament. Google designed an ASIC specifically for 
the task of accelerating their neural networks, and made thousands of them 
available for massive tests and training.  Terry McIntyre 
 Unix/Linux Systems Administration Taking time to do 
it right saves having to do it twice.tr 

On Thursday, January 5, 2017 9:01 AM, Stefan Kaitschick 
 wrote:
 

 

Honestly I got a little frustrated that many people didn't think that
was AlphaGo. It was almost clear to me because I know the difficulty of
developing AlphaGo-like bots.



 I feel with you. People seem to think that the Nature paper gave away the full 
recipe.

___
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

Re: [Computer-go] Our Silicon Overlord

[Jim O'Flaherty]

For each arcane position reached, there would now be ample data for AlphaGo
to train on that particular pathway. And it would emerge two strategies.
The first would be to avoid the state in the first place. And the second
would be to optimize play in that particular state. So, the human advantage
would be very short lived.

On Thu, Jan 5, 2017 at 12:37 AM, Robert Jasiek  wrote:

> On 04.01.2017 22:08, "Ingo Althöfer" wrote:
>
>> humanity's last hope
>>
>
> The "last hope" are theoreticians creating arcane positions far outside
> the NN of AlphaGo so that its deep reading would be insufficient
> compensation! Another chance is long-term, subtle creation and use of aji.
>
> --
> robert jasiek
>
> ___
> 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

Re: [Computer-go] Are the AlphaGols coming?

[Thomas Rohde]

Thanks, Horace,


On 2017-01-05 at 04:07, Horace Ho  wrote:

> The players and the results (in Chinese):
> 
> [..]

passing this on :-) 


Greetings, Tom
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] it's alphago

[Stefan Kaitschick]

> Honestly I got a little frustrated that many people didn't think that
> was AlphaGo. It was almost clear to me because I know the difficulty of
> developing AlphaGo-like bots.
>


 I feel with you. People seem to think that the Nature paper gave away the
full recipe.
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] SGF

[Andries E. Brouwer]

On Fri, Dec 30, 2016 at 01:28:34PM -0700, Anders Kierulf wrote:

>> It would be good if your document would clearly state which properties
>> are part of the FF[4] standard and which ones you’re adding.
>> For example, JD (Japanese Date) is not in FF[4], yet is listed as
>> “standardized in this document”. It’s possible that such a property
>> should be added, but any properties added to FF[4] need to be
>> clearly marked so they can discussed.

I replied to this and some other things, but it took the reply
some days before it appeared on the list. Anders, I hope you
saw that reply.

> Of the above, the six properties BC, JD, LC, LT, OH, WC are not in FF[4].
> These properties are
> 
> BC  Black Country
> WC  White Country
> JD  Japanese Date
> LC  Number of byo-yomi periods
> LT  Length of byo-yomi periods
> OH  Old Handicap

Here I want to elaborate on the "discuss" part.

At the time FF[4] was being defined, it was useful to discuss
what properties should be added, and with what syntax.

Unfortunately, SGF was left for many years without maintenance.
If some property was needed, people just invented and used something.
Different servers used different property labels for the same thing.
Today Chinese and Korean servers use what they use, and thousands
(indeed, millions) of game records exist with that usage.
They are not going to change their format because of any discussion here.

So, we are not in a position to define what must be used.
But we are in a position to describe what is commonly used,
so that people needing something can use what is used elsewhere.
And we can express preferences.

For example, the Foxwq server was started, and needed property labels
for Number and Length of byo-yomi periods, and chose TC and TT.
So, today OT[3x30s] and LC[3] LT[30] and TC[3] TT[30] are all used
to describe time settings for Master (AlphaGo) versus various opponents.
Since TC already has several other meanings, LC, LT seem a better choice
than TC, TT.

Andries


___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Reminder: Handicap-29 Prize

[Ingo Althöfer]

Hi,

a few years ago we had agreed that for winning the bet it would be
sufficient to beat the non-deterministic 12-kyu level of MFoG 11
(or MFoG 12). This level has no Monte Carlo elements ionvolved.

Ingo.
 
 

Gesendet: Donnerstag, 05. Januar 2017 um 04:15 Uhr
Von: fotl...@smart-games.com
An: computer-go@computer-go.org
Betreff: Re: [Computer-go] Reminder: Handicap-29 Prize

Yes. I’m travelling this week, but when I get home I can look for it. I’m not 
sure I can find the old source backups to make a gtp version.
 
David
 
From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Álvaro Begué
Sent: Wednesday, January 4, 2017 4:48 PM
To: computer-go 
Subject: Re: [Computer-go] Reminder: Handicap-29 Prize
 

Would you be willing to make the executable of mfgo1998 available so we can run 
it locally? Or even better, something with the same engine but which speaks GTP?

 

Álvaro.

 

 

 

 

 

On Wed, Jan 4, 2017 at 10:32 PM, "Ingo Althöfer" 
<3-hirn-ver...@gmx.de[mailto:3-hirn-ver...@gmx.de]> wrote:
Like in every year, the reminder on my Handicap-29 prize:
http://www.althofer.de/handicap-29-prize.html[http://www.althofer.de/handicap-29-prize.html]

I think, AlphaGo in its current form would not have a chance to cash in ;-)

Ingo.
___
Computer-go mailing list
Computer-go@computer-go.org[mailto: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[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

Re: [Computer-go] Are the AlphaGols coming?

[Paweł Morawiecki]

>
>
> what makes you think the opening theory with reverse komi would be the
> same as with standard komi?
>
> The value network only needs to know a given position of the board and a
piece of information who plays next, whether it is a green player or a red
player. Then it tells you a winning percentage for a green player. Does it
make sense?

Best,
Paweł





> I would be afraid to invest an enormous amount of time just to learn,
> that you have to open differently in reverse komi games :)
>
>
> Detlef
>
> Am 05.01.2017 um 10:50 schrieb Paweł Morawiecki:
> > 2017-01-04 21:07 GMT+01:00 David Ongaro :
> >
> >>
> >> [...]So my question is: is it possible to have reverse Komi games
> >> by feeding the value network with reverse colors?
> >>
> >
> > In the paper from Nature (subsection "Features for policy/value
> > network"), authors state:
> >
> > *the stone colour at each intersection was represented as either
> > player or opponent rather than black or white. *
> >
> > Then, I think the AlphaGo algorithm would be fine with a reverse
> > komi. Namely, a human player takes black and has 7.5 komi. The next
> > step is that AlphaGo gives 2 stones of handicap but keeps 7.5 komi
> > (normally you have 0.5).
> >
> > Aja, can you confirm this?
> >
> >
> >> Also having 2 stone games is not so interesting since it would
> >> reveal less insights for even game opening Theory.
> >>
> >
> > I agree with David here, most insights we would get from even
> > games. But we can imagine the following show. Some games are played
> > with a reverse komi, some games would be played with 2 stones (yet,
> > white keeps 7.5 komi) and eventually the main event with normal
> > even games to debunk our myths on the game. Wouldn't be super
> > exciting!?
> >
> > Best regards, Paweł
> >
> >
> >
> > ___ 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/computer-go

Re: [Computer-go] Are the AlphaGols coming?

[Detlef Schmicker]

Hi,

what makes you think the opening theory with reverse komi would be the
same as with standard komi?

I would be afraid to invest an enormous amount of time just to learn,
that you have to open differently in reverse komi games :)


Detlef

Am 05.01.2017 um 10:50 schrieb Paweł Morawiecki:
> 2017-01-04 21:07 GMT+01:00 David Ongaro :
> 
>> 
>> [...]So my question is: is it possible to have reverse Komi games
>> by feeding the value network with reverse colors?
>> 
> 
> In the paper from Nature (subsection "Features for policy/value
> network"), authors state:
> 
> *the stone colour at each intersection was represented as either
> player or opponent rather than black or white. *
> 
> Then, I think the AlphaGo algorithm would be fine with a reverse
> komi. Namely, a human player takes black and has 7.5 komi. The next
> step is that AlphaGo gives 2 stones of handicap but keeps 7.5 komi
> (normally you have 0.5).
> 
> Aja, can you confirm this?
> 
> 
>> Also having 2 stone games is not so interesting since it would
>> reveal less insights for even game opening Theory.
>> 
> 
> I agree with David here, most insights we would get from even
> games. But we can imagine the following show. Some games are played
> with a reverse komi, some games would be played with 2 stones (yet,
> white keeps 7.5 komi) and eventually the main event with normal
> even games to debunk our myths on the game. Wouldn't be super
> exciting!?
> 
> Best regards, Paweł
> 
> 
> 
> ___ 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

Re: [Computer-go] Are the AlphaGols coming?

[Paweł Morawiecki]

2017-01-04 21:07 GMT+01:00 David Ongaro :

>
> [...]So my question is: is it possible to have reverse Komi games by
> feeding the value network with reverse colors?
>

In the paper from Nature (subsection "Features for policy/value network"),
authors state:

*the stone colour at each intersection was represented as either player or
opponent rather than black or white. *

Then, I think the AlphaGo algorithm would be fine with a reverse komi.
Namely, a human player takes black and has 7.5 komi. The next step is that
AlphaGo gives 2 stones of handicap but keeps 7.5 komi (normally you have
0.5).

Aja, can you confirm this?


> Also having 2 stone games is not so interesting since it would reveal less
> insights for even game opening Theory.
>

I agree with David here, most insights we would get from even games. But we
can imagine the following show. Some games are played with a reverse komi,
some games would be played with 2 stones (yet, white keeps 7.5 komi) and
eventually the main event with normal even games to debunk our myths on the
game. Wouldn't be super exciting!?

Best regards,
Paweł
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go