Re: [Computer-go] Zen lost to Mi Yu Ting

[John Tromp]

>> (Japanese rules are not *that* hard. IIRC, Many Faces, and all other
>> programs, including my own, scored in them
>
> There is a huge difference between doing some variation of territory
> scoring and implementing Japanese rules. Understanding this difference
> will get you some way to understanding why some people do not like them,
> and that has got nothing to do with computer go.

I do not like them because, as far as i can tell, they cannot answer
questions like: what is fair komi for 2x2 Go (i.e. what is the outcome
with perfect play) ?

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

Re: [Computer-go] Zen lost to Mi Yu Ting

[Gian-Carlo Pascutto]

On 22-03-17 16:27, Darren Cook wrote:
> (Japanese rules are not *that* hard. IIRC, Many Faces, and all other
> programs, including my own, scored in them

There is a huge difference between doing some variation of territory
scoring and implementing Japanese rules. Understanding this difference
will get you some way to understanding why some people do not like them,
and that has got nothing to do with computer go.

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

Re: [Computer-go] Zen lost to Mi Yu Ting

[Darren Cook]

>>> The issue with Japanese rules is easily solved by refusing to play
>>> under ridiculous rules. Yes, I do have strong opinions. :)
>>
>> And the problem with driver-less cars is easily "solved" by banning
>> all road users that are not also driver-less cars (including all 
>> pedestrians, bikes and wild animals).
> 
> I think you misunderstand the sentiment completely. It is not: Japanese
> rules are difficult for computers, so we don't like them.
> 
> It is: Japanese rules are problematic on many levels, ...

Yes, that was the sentiment I understood. Chinese rules (Tromp-Taylor,
etc.) are nice and clean, so easy to implement. They were useful props
to make the progress up until now. The real world is messy and
illogical, as are the corner cases in Japanese rules. Assuming you are
in this for the AI learnings, not just to make a strong Chinese-rules go
program, why not embrace the messiness!

(Japanese rules are not *that* hard. IIRC, Many Faces, and all other
programs, including my own, scored in them, before MCTS took hold and
being able to shave milliseconds off scoring became the main decider of
a program's strength.)

Darren


-- 
Darren Cook, Software Researcher/Developer
My New Book: Practical Machine Learning with H2O:
  http://shop.oreilly.com/product/0636920053170.do
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Zen lost to Mi Yu Ting

[Álvaro Begué]

Thank you, Gian-Carlo. I couldn't have said it better.

Álvaro.



On Wed, Mar 22, 2017 at 7:07 AM, Gian-Carlo Pascutto  wrote:

> On 22-03-17 09:41, Darren Cook wrote:
> >> The issue with Japanese rules is easily solved by refusing to play
> >> under ridiculous rules. Yes, I do have strong opinions. :)
> >
> > And the problem with driver-less cars is easily "solved" by banning
> > all road users that are not also driver-less cars (including all
> > pedestrians, bikes and wild animals).
>
> I think you misunderstand the sentiment completely. It is not: Japanese
> rules are difficult for computers, so we don't like them.
>
> It is: Japanese rules are problematic on many levels, so we prefer to
> work with Chinese ones and as a consequence that's what the programs are
> trained for and tested on. It is telling that Zen is having these
> troubles despite being made by Japanese programmers. I believe the
> saying for this is "voting with your feet".
>
> > Or how about this angle: humans are still better than the programs
> > at Japanese rules. Therefore this is an interesting area of study.
>
> Maybe some people are interested in studying Japanese rules, like
> finding out what they actually are
> (http://home.snafu.de/jasiek/j1989c.html). That's fine, but not all that
> interesting for AI, or, actually, computer go.
>
> Of course, commercial programs that need to cater to a Japanese (or
> Korean) audience are stuck. As are people that want to play the UEC Cup
> etc.
>
> --
> GCP
> ___
> 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] Zen lost to Mi Yu Ting

[Gian-Carlo Pascutto]

On 22-03-17 09:41, Darren Cook wrote:
>> The issue with Japanese rules is easily solved by refusing to play
>> under ridiculous rules. Yes, I do have strong opinions. :)
> 
> And the problem with driver-less cars is easily "solved" by banning
> all road users that are not also driver-less cars (including all 
> pedestrians, bikes and wild animals).

I think you misunderstand the sentiment completely. It is not: Japanese
rules are difficult for computers, so we don't like them.

It is: Japanese rules are problematic on many levels, so we prefer to
work with Chinese ones and as a consequence that's what the programs are
trained for and tested on. It is telling that Zen is having these
troubles despite being made by Japanese programmers. I believe the
saying for this is "voting with your feet".

> Or how about this angle: humans are still better than the programs
> at Japanese rules. Therefore this is an interesting area of study.

Maybe some people are interested in studying Japanese rules, like
finding out what they actually are
(http://home.snafu.de/jasiek/j1989c.html). That's fine, but not all that
interesting for AI, or, actually, computer go.

Of course, commercial programs that need to cater to a Japanese (or
Korean) audience are stuck. As are people that want to play the UEC Cup etc.

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

Re: [Computer-go] Zen lost to Mi Yu Ting

[Darren Cook]

> The issue with Japanese rules is easily solved by refusing to play under 
> ridiculous rules. Yes, I do have strong opinions. :)

And the problem with driver-less cars is easily "solved" by banning all
road users that are not also driver-less cars (including all
pedestrians, bikes and wild animals).

Or how about this angle: humans are still better than the programs at
Japanese rules. Therefore this is an interesting area of study.

Darren




-- 
Darren Cook, Software Researcher/Developer
My New Book: Practical Machine Learning with H2O:
  http://shop.oreilly.com/product/0636920053170.do
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Zen lost to Mi Yu Ting

[Gian-Carlo Pascutto]

On 22-03-17 00:36, cazen...@ai.univ-paris8.fr wrote:
> 
> Why can't you reuse the same self played games but score them

If you have self-play games that are played to the final position so
scoring is fool-proof, then it could work. But I think things get really
interesting when timing of a pass matters (which is the kind of
situation we're trying to resolve) and you're using pure policy players.

Does your DCNN only player know *precisely* when to pass *first* under
Japanese rules?

> The policy network does not use the komi to choose its moves so it
> should make no difference.

Do you not play different moves when you are behind 0.5 points compared
to when you're ahead 0.5 points?

(Or if you're ignoring komi completely, behind multiple stones vs ahead
multiple stones?)

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

Re: [Computer-go] Zen lost to Mi Yu Ting

[Detlef Schmicker]

oakfoam value network does exactly this, we have 6 komi layers -7.5 -5.5
-0.5 0.5 5.5 7.5 (+ and - due to color played) and trained from 4d+ kgs
games with this:
if (c_played==1):
  if ("0.5" in komi):
komiplane=1;
  if ("6.5" in komi or "2.75" in komi or "5.5" in komi):
#komi 6.5 and 5.5 not very different in chinese scoring
komiplane=2;
  if ("7.5" in komi or "3.75" in komi):
komiplane=3;
if (c_played==2):
  if ("0.5" in komi):
komiplane=4;
  if ("6.5" in komi or "2.75" in komi or "5.5" in komi):
#komi 6.5 and 5.5 not very different in chinese scoring
komiplane=5;
  if ("7.5" in komi or "3.75" in komi):
komiplane=6;


But I was unable to get a sgf file from the japanese language site :)

I did not really test if this layers help, but they are there and
trained and you might check yourself :)

Detlef

Am 21.03.2017 um 21:08 schrieb David Ongaro:
> On Mar 21, 2017, at 7:00 AM, Paweł Morawiecki  
> wrote:
>>
>> Hideki,
>>
>>  Using this for Japanese and 6.5, there will be some
>> error in close games.  We knew this issue and thought such
>> chances would be so small that postponed correcting (not so
>> easy).
>>
>> But how would you fix it? Isn't that you'd need to retrain your value 
>> network from the scratch?
> 
> I would think so as well. But I some months ago I already made a proposal in 
> this list to mitigate that problem: instead of training a different value 
> network for each Komi, add a “Komi adjustment” value as input during the 
> training phase. That should be much more effective, since the “win/lost” 
> evaluation shouldn’t change for many (most?) positions for small adjustments 
> but the resulting value network (when trained for different Komi adjustments) 
> has a much greater range of applicability.
> 
> Regards
> 
> David O.
> 
> 
>>
>> Oh, so that's why! Good luck with Zen's next two games. 
>>
>> Aja
>>  
>> Best,
>> Hideki
>>
>> Pawe  Morawiecki: 
>> > >:
>>> Hi,
>>>
>>> After an interesting game DeepZen lost to Mi Yu Ting.
>>> Here you can replay the complete game:
>>> http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13 
>>> 
>>>
>>> According to pro experts, Zen fought really well, but it seems there is
>>> still some issue how Zen (mis)evaluates its chances. At one point it showed
>>> 84% chance of winning (in the endgame), whereas it was already quite clear
>>> Zen is little behind (2-3 points).
>>>
>>> Regards,
>>> Pawel
>>>  inline file
>>> ___
>>> Computer-go mailing list
>>> Computer-go@computer-go.org 
>>> http://computer-go.org/mailman/listinfo/computer-go 
>>> 
>> --
>> Hideki Kato >
>> ___
>> 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
> 
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Zen lost to Mi Yu Ting

[Álvaro Begué]

I was thinking the same thing. You can easily equip the value network with
several outputs, corresponding to several settings of komi, then train as
usual.

The issue with Japanese rules is easily solved by refusing to play under
ridiculous rules. Yes, I do have strong opinions. :)

Álvaro.



On Tue, Mar 21, 2017 at 7:36 PM,  wrote:

>
> Why can't you reuse the same self played games but score them with a
> different komi value ? The policy network does not use the komi to choose
> its moves so it should make no difference.
>
>
> > On 21/03/2017 21:08, David Ongaro wrote:
> >>> But how would you fix it? Isn't that you'd need to retrain your value
> >>> network from the scratch?
> >>
> >> I would think so as well. But I some months ago I already made a
> >> proposal in this list to mitigate that problem: instead of training a
> >> different value network for each Komi, add a “Komi adjustment† value
> >> as
> >> input during the training phase. That should be much more effective,
> >> since the “win/lost† evaluation shouldn’t change for many (most?)
> >> positions for small adjustments but the resulting value network (when
> >> trained for different Komi adjustments) has a much greater range of
> >> applicability.
> >
> > The problem is not the training of the network itself (~2-4 weeks of
> > letting a program someone else wrote run in the background, easiest
> > thing ever in computer go), or whether you use a komi input or a
> > separate network, the problem is getting data for the different komi
> > values.
> >
> > Note that if getting data is not a problem, then a separate network
> > would perform better than your proposal.
> >
> > --
> > GCP
> > ___
> > 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] Zen lost to Mi Yu Ting

[uurtamo .]

I guess that 1 point in such a game matters to the evaluation function.
Pretty fascinating. Can you not train for the two different rulesets and
just pick which at the beginning? Ignoring Chinese versus Japanese, just
training on komi? Or is the problem of Japanese rules the whole issue? (I.e
not komi)?

On Tuesday, March 21, 2017, Hideki Kato  wrote:

> The value network has been trained with Chinese rules and 7.5
> pts komi.  Using this for Japanese and 6.5, there will be some
> error in close games.  We knew this issue and thought such
> chances would be so small that postponed correcting (not so
> easy).
>
> Best,
> Hideki
>
> Pawe  Morawiecki: <
> caksbshpvd34hvjt-b+x73rdpg5-4wsxoezykbheslprewci...@mail.gmail.com
> >:
> >Hi,
> >
> >After an interesting game DeepZen lost to Mi Yu Ting.
> >Here you can replay the complete game:
> >http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13
> >
> >According to pro experts, Zen fought really well, but it seems there is
> >still some issue how Zen (mis)evaluates its chances. At one point it
> showed
> >84% chance of winning (in the endgame), whereas it was already quite clear
> >Zen is little behind (2-3 points).
> >
> >Regards,
> >Pawel
> > inline file
> >___
> >Computer-go mailing list
> >Computer-go@computer-go.org 
> >http://computer-go.org/mailman/listinfo/computer-go
> --
> Hideki Kato >
> ___
> 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] Zen lost to Mi Yu Ting

[Chun Sun]

How does Zen know it's playing a Japanese rule game? Can it be set to play
a Chinese rule game and hope to converge at the end?

On Mar 21, 2017 8:03 AM, "Hideki Kato"  wrote:

> The value network has been trained with Chinese rules and 7.5
> pts komi.  Using this for Japanese and 6.5, there will be some
> error in close games.  We knew this issue and thought such
> chances would be so small that postponed correcting (not so
> easy).
>
> Best,
> Hideki
>
> Pawe  Morawiecki:  4wsxoezykbheslprewci...@mail.gmail.com>:
> >Hi,
> >
> >After an interesting game DeepZen lost to Mi Yu Ting.
> >Here you can replay the complete game:
> >http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13
> >
> >According to pro experts, Zen fought really well, but it seems there is
> >still some issue how Zen (mis)evaluates its chances. At one point it
> showed
> >84% chance of winning (in the endgame), whereas it was already quite clear
> >Zen is little behind (2-3 points).
> >
> >Regards,
> >Pawel
> > inline file
> >___
> >Computer-go mailing list
> >Computer-go@computer-go.org
> >http://computer-go.org/mailman/listinfo/computer-go
> --
> Hideki Kato 
> ___
> 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] Zen lost to Mi Yu Ting

[cazenave]

Why can't you reuse the same self played games but score them with a
different komi value ? The policy network does not use the komi to choose
its moves so it should make no difference.


> On 21/03/2017 21:08, David Ongaro wrote:
>>> But how would you fix it? Isn't that you'd need to retrain your value
>>> network from the scratch?
>>
>> I would think so as well. But I some months ago I already made a
>> proposal in this list to mitigate that problem: instead of training a
>> different value network for each Komi, add a “Komi adjustment” value
>> as
>> input during the training phase. That should be much more effective,
>> since the “win/lost” evaluation shouldn’t change for many (most?)
>> positions for small adjustments but the resulting value network (when
>> trained for different Komi adjustments) has a much greater range of
>> applicability.
>
> The problem is not the training of the network itself (~2-4 weeks of
> letting a program someone else wrote run in the background, easiest
> thing ever in computer go), or whether you use a komi input or a
> separate network, the problem is getting data for the different komi
> values.
>
> Note that if getting data is not a problem, then a separate network
> would perform better than your proposal.
>
> --
> GCP
> ___
> 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] Zen lost to Mi Yu Ting

[Gian-Carlo Pascutto]

On 21/03/2017 21:08, David Ongaro wrote:
>> But how would you fix it? Isn't that you'd need to retrain your value
>> network from the scratch?
> 
> I would think so as well. But I some months ago I already made a
> proposal in this list to mitigate that problem: instead of training a
> different value network for each Komi, add a “Komi adjustment” value as
> input during the training phase. That should be much more effective,
> since the “win/lost” evaluation shouldn’t change for many (most?)
> positions for small adjustments but the resulting value network (when
> trained for different Komi adjustments) has a much greater range of
> applicability.

The problem is not the training of the network itself (~2-4 weeks of
letting a program someone else wrote run in the background, easiest
thing ever in computer go), or whether you use a komi input or a
separate network, the problem is getting data for the different komi values.

Note that if getting data is not a problem, then a separate network
would perform better than your proposal.

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

Re: [Computer-go] Zen lost to Mi Yu Ting

[Paweł Morawiecki]

Hideki,

 Using this for Japanese and 6.5, there will be some
>> error in close games.  We knew this issue and thought such
>> chances would be so small that postponed correcting (not so
>> easy).
>>
>
But how would you fix it? Isn't that you'd need to retrain your value
network from the scratch?

Regards,
Paweł


>
> Oh, so that's why! Good luck with Zen's next two games.
>
> Aja
>
>
>> Best,
>> Hideki
>>
>> Pawe  Morawiecki: > wsxoezykbheslprewci...@mail.gmail.com>:
>> >Hi,
>> >
>> >After an interesting game DeepZen lost to Mi Yu Ting.
>> >Here you can replay the complete game:
>> >http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13
>> >
>> >According to pro experts, Zen fought really well, but it seems there is
>> >still some issue how Zen (mis)evaluates its chances. At one point it
>> showed
>> >84% chance of winning (in the endgame), whereas it was already quite
>> clear
>> >Zen is little behind (2-3 points).
>> >
>> >Regards,
>> >Pawel
>> > inline file
>> >___
>> >Computer-go mailing list
>> >Computer-go@computer-go.org
>> >http://computer-go.org/mailman/listinfo/computer-go
>> --
>> Hideki Kato 
>> ___
>> 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] Zen lost to Mi Yu Ting

[Aja Huang via Computer-go]

On Tue, Mar 21, 2017 at 10:48 AM, Hideki Kato 
wrote:

> The value network has been trained with Chinese rules and 7.5
> pts komi.  Using this for Japanese and 6.5, there will be some
> error in close games.  We knew this issue and thought such
> chances would be so small that postponed correcting (not so
> easy).
>

Oh, so that's why! Good luck with Zen's next two games.

Aja


> Best,
> Hideki
>
> Pawe  Morawiecki:  4wsxoezykbheslprewci...@mail.gmail.com>:
> >Hi,
> >
> >After an interesting game DeepZen lost to Mi Yu Ting.
> >Here you can replay the complete game:
> >http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13
> >
> >According to pro experts, Zen fought really well, but it seems there is
> >still some issue how Zen (mis)evaluates its chances. At one point it
> showed
> >84% chance of winning (in the endgame), whereas it was already quite clear
> >Zen is little behind (2-3 points).
> >
> >Regards,
> >Pawel
> > inline file
> >___
> >Computer-go mailing list
> >Computer-go@computer-go.org
> >http://computer-go.org/mailman/listinfo/computer-go
> --
> Hideki Kato 
> ___
> 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] Zen lost to Mi Yu Ting

[Hideki Kato]

The value network has been trained with Chinese rules and 7.5 
pts komi.  Using this for Japanese and 6.5, there will be some 
error in close games.  We knew this issue and thought such 
chances would be so small that postponed correcting (not so 
easy).

Best,
Hideki

Pawe Morawiecki: 
:
>Hi,
>
>After an interesting game DeepZen lost to Mi Yu Ting.
>Here you can replay the complete game:
>http://duiyi.sina.com.cn/gibo_new/live/viewer.asp?sno=13
>
>According to pro experts, Zen fought really well, but it seems there is
>still some issue how Zen (mis)evaluates its chances. At one point it showed
>84% chance of winning (in the endgame), whereas it was already quite clear
>Zen is little behind (2-3 points).
>
>Regards,
>Pawel
> inline file
>___
>Computer-go mailing list
>Computer-go@computer-go.org
>http://computer-go.org/mailman/listinfo/computer-go
-- 
Hideki Kato 
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go