Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Ryan Hayward]

no

On Thu, Mar 31, 2016 at 8:33 AM, Lucas, Simon M <s...@essex.ac.uk> wrote:

> Thanks Ryan,
>
> Nice paper – did you follow up on any of the future work?
>
>   Simon
>
>
>
> From: Computer-go <computer-go-boun...@computer-go.org> on behalf of Ryan
> Hayward <hayw...@ualberta.ca>
> Reply-To: "computer-go@computer-go.org" <computer-go@computer-go.org>
> Date: Wednesday, 30 March 2016 at 18:59
> To: "computer-go@computer-go.org" <computer-go@computer-go.org>
> Subject: Re: [Computer-go] Congratulations to AlphaGo (Statistical
> significance of results)
>
> Hey Simon,
>
> I only now remembered:
>
> we actually experimented on the effect
> of making 1 blunder (random move instead of learned/searched move)
> in Go and Hex
>
> "Blunder Cost in Go and Hex"
>
> so this might be a starting point for your question
> of measuring player strength by measuring
> all move strengths...
>
> https://webdocs.cs.ualberta.ca/~hayward/papers/blunder.pdf
>
> On Wed, Mar 30, 2016 at 5:29 AM, Lucas, Simon M <s...@essex.ac.uk> wrote:
>
>> In my original post I put a link to
>> the relevant section of the MacKay
>> book that shows exactly how to calculate
>> the probability of superiority
>> assuming the game outcome is modelled as
>> a biased coin toss:
>>
>> http://www.inference.phy.cam.ac.uk/itila/
>>
>>
>> I was making the point that for this
>>
>> and for other outcomes of skill-based games
>> we can do so much more (and as humans we intuitively
>> DO do so much more) than just look at the event
>> outcome - and maybe as a community we should do that more
>> routinely and more quantitatively (e.g.
>> by analysing the quality of each move / action)
>>
>> Best wishes,
>>
>>   Simon
>>
>>
>>
>> On 30/03/2016, 11:57, "Computer-go on behalf of djhbrown ." <
>> computer-go-boun...@computer-go.org on behalf of djhbr...@gmail.com>
>> wrote:
>>
>> >Simon wrote: "I was discussing the results with a colleague outside
>> >of the Game AI area the other day when he raised
>> >the question (which applies to nearly all sporting events,
>> >given the small sample size involved)
>> >of statistical significance - suggesting that on another week
>> >the result might have been 4-1 to Lee Sedol."
>> >
>> >call me naive, but perhaps you could ask your colleague to calculate
>> >the probability one of side winning 4 games out of 5, and then say
>> >whether that is within 2 standard deviations of the norm.
>> >
>> >his suggestion is complete nonsense, regardless of the small sample
>> >size.  perhaps you could ask a statistician next time.
>> >
>> >--
>> >patient: "whenever i open my mouth, i get a shooting pain in my foot"
>> >doctor: "fire!"
>> >http://sites.google.com/site/djhbrown2/home
>> >https://www.youtube.com/user/djhbrown
>> >___
>> >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
>>
>
>
>
> --
> Ryan B Hayward
> Professor and Director (Outreach+Diversity)
> Computing Science,  UAlberta
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>



-- 
Ryan B Hayward
Professor and Director (Outreach+Diversity)
Computing Science,  UAlberta
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Lucas, Simon M]

Thanks Ryan,

Nice paper – did you follow up on any of the future work?

  Simon



From: Computer-go 
<computer-go-boun...@computer-go.org<mailto:computer-go-boun...@computer-go.org>>
 on behalf of Ryan Hayward <hayw...@ualberta.ca<mailto:hayw...@ualberta.ca>>
Reply-To: "computer-go@computer-go.org<mailto:computer-go@computer-go.org>" 
<computer-go@computer-go.org<mailto:computer-go@computer-go.org>>
Date: Wednesday, 30 March 2016 at 18:59
To: "computer-go@computer-go.org<mailto:computer-go@computer-go.org>" 
<computer-go@computer-go.org<mailto:computer-go@computer-go.org>>
Subject: Re: [Computer-go] Congratulations to AlphaGo (Statistical significance 
of results)

Hey Simon,

I only now remembered:

we actually experimented on the effect
of making 1 blunder (random move instead of learned/searched move)
in Go and Hex

"Blunder Cost in Go and Hex"

so this might be a starting point for your question
of measuring player strength by measuring
all move strengths...

https://webdocs.cs.ualberta.ca/~hayward/papers/blunder.pdf

On Wed, Mar 30, 2016 at 5:29 AM, Lucas, Simon M 
<s...@essex.ac.uk<mailto:s...@essex.ac.uk>> wrote:
In my original post I put a link to
the relevant section of the MacKay
book that shows exactly how to calculate
the probability of superiority
assuming the game outcome is modelled as
a biased coin toss:

http://www.inference.phy.cam.ac.uk/itila/


I was making the point that for this

and for other outcomes of skill-based games
we can do so much more (and as humans we intuitively
DO do so much more) than just look at the event
outcome - and maybe as a community we should do that more
routinely and more quantitatively (e.g.
by analysing the quality of each move / action)

Best wishes,

  Simon



On 30/03/2016, 11:57, "Computer-go on behalf of djhbrown ." 
<computer-go-boun...@computer-go.org<mailto:computer-go-boun...@computer-go.org>
 on behalf of djhbr...@gmail.com<mailto:djhbr...@gmail.com>> wrote:

>Simon wrote: "I was discussing the results with a colleague outside
>of the Game AI area the other day when he raised
>the question (which applies to nearly all sporting events,
>given the small sample size involved)
>of statistical significance - suggesting that on another week
>the result might have been 4-1 to Lee Sedol."
>
>call me naive, but perhaps you could ask your colleague to calculate
>the probability one of side winning 4 games out of 5, and then say
>whether that is within 2 standard deviations of the norm.
>
>his suggestion is complete nonsense, regardless of the small sample
>size.  perhaps you could ask a statistician next time.
>
>--
>patient: "whenever i open my mouth, i get a shooting pain in my foot"
>doctor: "fire!"
>http://sites.google.com/site/djhbrown2/home
>https://www.youtube.com/user/djhbrown
>___
>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<mailto:Computer-go@computer-go.org>
http://computer-go.org/mailman/listinfo/computer-go



--
Ryan B Hayward
Professor and Director (Outreach+Diversity)
Computing Science,  UAlberta
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[uurtamo .]

Or, if it's lopsided far from 1/2, Wilson's is just as good, in my
experience.
On Mar 30, 2016 10:29 AM, "Olivier Teytaud"  wrote:

> don't use asymptotic normality with a sample size 5, use Fisher's exact
> test
>
> the p-value for the rejection of
> "P(alpha-Go wins a given game against Lee Sedol)<.5"
> might be something like 3/16
> (under the "independent coin" assumption!)
>
> this is not 0.05, but still quite an impressive result :-)
>
> with 5-0 it would have been <0.05.
>
>
>
> On Wed, Mar 30, 2016 at 6:59 PM, Ryan Hayward  wrote:
>
>> Hey Simon,
>>
>> I only now remembered:
>>
>> we actually experimented on the effect
>> of making 1 blunder (random move instead of learned/searched move)
>> in Go and Hex
>>
>> "Blunder Cost in Go and Hex"
>>
>> so this might be a starting point for your question
>> of measuring player strength by measuring
>> all move strengths...
>>
>> https://webdocs.cs.ualberta.ca/~hayward/papers/blunder.pdf
>>
>> On Wed, Mar 30, 2016 at 5:29 AM, Lucas, Simon M  wrote:
>>
>>> In my original post I put a link to
>>> the relevant section of the MacKay
>>> book that shows exactly how to calculate
>>> the probability of superiority
>>> assuming the game outcome is modelled as
>>> a biased coin toss:
>>>
>>> http://www.inference.phy.cam.ac.uk/itila/
>>>
>>>
>>> I was making the point that for this
>>>
>>> and for other outcomes of skill-based games
>>> we can do so much more (and as humans we intuitively
>>> DO do so much more) than just look at the event
>>> outcome - and maybe as a community we should do that more
>>> routinely and more quantitatively (e.g.
>>> by analysing the quality of each move / action)
>>>
>>> Best wishes,
>>>
>>>   Simon
>>>
>>>
>>>
>>> On 30/03/2016, 11:57, "Computer-go on behalf of djhbrown ." <
>>> computer-go-boun...@computer-go.org on behalf of djhbr...@gmail.com>
>>> wrote:
>>>
>>> >Simon wrote: "I was discussing the results with a colleague outside
>>> >of the Game AI area the other day when he raised
>>> >the question (which applies to nearly all sporting events,
>>> >given the small sample size involved)
>>> >of statistical significance - suggesting that on another week
>>> >the result might have been 4-1 to Lee Sedol."
>>> >
>>> >call me naive, but perhaps you could ask your colleague to calculate
>>> >the probability one of side winning 4 games out of 5, and then say
>>> >whether that is within 2 standard deviations of the norm.
>>> >
>>> >his suggestion is complete nonsense, regardless of the small sample
>>> >size.  perhaps you could ask a statistician next time.
>>> >
>>> >--
>>> >patient: "whenever i open my mouth, i get a shooting pain in my foot"
>>> >doctor: "fire!"
>>> >http://sites.google.com/site/djhbrown2/home
>>> >https://www.youtube.com/user/djhbrown
>>> >___
>>> >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
>>>
>>
>>
>>
>> --
>> Ryan B Hayward
>> Professor and Director (Outreach+Diversity)
>> Computing Science,  UAlberta
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
>
>
> --
> =
> Olivier Teytaud, olivier.teyt...@inria.fr, TAO, LRI, UMR 8623(CNRS -
> Univ. Paris-Sud),
> bat 490 Univ. Paris-Sud F-91405 Orsay Cedex France
> http://www.slideshare.net/teytaud
>
>
> ___
> 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] Congratulations to AlphaGo (Statistical significance of results)

[Olivier Teytaud]

don't use asymptotic normality with a sample size 5, use Fisher's exact test

the p-value for the rejection of
"P(alpha-Go wins a given game against Lee Sedol)<.5"
might be something like 3/16
(under the "independent coin" assumption!)

this is not 0.05, but still quite an impressive result :-)

with 5-0 it would have been <0.05.



On Wed, Mar 30, 2016 at 6:59 PM, Ryan Hayward  wrote:

> Hey Simon,
>
> I only now remembered:
>
> we actually experimented on the effect
> of making 1 blunder (random move instead of learned/searched move)
> in Go and Hex
>
> "Blunder Cost in Go and Hex"
>
> so this might be a starting point for your question
> of measuring player strength by measuring
> all move strengths...
>
> https://webdocs.cs.ualberta.ca/~hayward/papers/blunder.pdf
>
> On Wed, Mar 30, 2016 at 5:29 AM, Lucas, Simon M  wrote:
>
>> In my original post I put a link to
>> the relevant section of the MacKay
>> book that shows exactly how to calculate
>> the probability of superiority
>> assuming the game outcome is modelled as
>> a biased coin toss:
>>
>> http://www.inference.phy.cam.ac.uk/itila/
>>
>>
>> I was making the point that for this
>>
>> and for other outcomes of skill-based games
>> we can do so much more (and as humans we intuitively
>> DO do so much more) than just look at the event
>> outcome - and maybe as a community we should do that more
>> routinely and more quantitatively (e.g.
>> by analysing the quality of each move / action)
>>
>> Best wishes,
>>
>>   Simon
>>
>>
>>
>> On 30/03/2016, 11:57, "Computer-go on behalf of djhbrown ." <
>> computer-go-boun...@computer-go.org on behalf of djhbr...@gmail.com>
>> wrote:
>>
>> >Simon wrote: "I was discussing the results with a colleague outside
>> >of the Game AI area the other day when he raised
>> >the question (which applies to nearly all sporting events,
>> >given the small sample size involved)
>> >of statistical significance - suggesting that on another week
>> >the result might have been 4-1 to Lee Sedol."
>> >
>> >call me naive, but perhaps you could ask your colleague to calculate
>> >the probability one of side winning 4 games out of 5, and then say
>> >whether that is within 2 standard deviations of the norm.
>> >
>> >his suggestion is complete nonsense, regardless of the small sample
>> >size.  perhaps you could ask a statistician next time.
>> >
>> >--
>> >patient: "whenever i open my mouth, i get a shooting pain in my foot"
>> >doctor: "fire!"
>> >http://sites.google.com/site/djhbrown2/home
>> >https://www.youtube.com/user/djhbrown
>> >___
>> >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
>>
>
>
>
> --
> Ryan B Hayward
> Professor and Director (Outreach+Diversity)
> Computing Science,  UAlberta
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>



-- 
=
Olivier Teytaud, olivier.teyt...@inria.fr, TAO, LRI, UMR 8623(CNRS - Univ.
Paris-Sud),
bat 490 Univ. Paris-Sud F-91405 Orsay Cedex France
http://www.slideshare.net/teytaud
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Ryan Hayward]

Hey Simon,

I only now remembered:

we actually experimented on the effect
of making 1 blunder (random move instead of learned/searched move)
in Go and Hex

"Blunder Cost in Go and Hex"

so this might be a starting point for your question
of measuring player strength by measuring
all move strengths...

https://webdocs.cs.ualberta.ca/~hayward/papers/blunder.pdf

On Wed, Mar 30, 2016 at 5:29 AM, Lucas, Simon M  wrote:

> In my original post I put a link to
> the relevant section of the MacKay
> book that shows exactly how to calculate
> the probability of superiority
> assuming the game outcome is modelled as
> a biased coin toss:
>
> http://www.inference.phy.cam.ac.uk/itila/
>
>
> I was making the point that for this
>
> and for other outcomes of skill-based games
> we can do so much more (and as humans we intuitively
> DO do so much more) than just look at the event
> outcome - and maybe as a community we should do that more
> routinely and more quantitatively (e.g.
> by analysing the quality of each move / action)
>
> Best wishes,
>
>   Simon
>
>
>
> On 30/03/2016, 11:57, "Computer-go on behalf of djhbrown ." <
> computer-go-boun...@computer-go.org on behalf of djhbr...@gmail.com>
> wrote:
>
> >Simon wrote: "I was discussing the results with a colleague outside
> >of the Game AI area the other day when he raised
> >the question (which applies to nearly all sporting events,
> >given the small sample size involved)
> >of statistical significance - suggesting that on another week
> >the result might have been 4-1 to Lee Sedol."
> >
> >call me naive, but perhaps you could ask your colleague to calculate
> >the probability one of side winning 4 games out of 5, and then say
> >whether that is within 2 standard deviations of the norm.
> >
> >his suggestion is complete nonsense, regardless of the small sample
> >size.  perhaps you could ask a statistician next time.
> >
> >--
> >patient: "whenever i open my mouth, i get a shooting pain in my foot"
> >doctor: "fire!"
> >http://sites.google.com/site/djhbrown2/home
> >https://www.youtube.com/user/djhbrown
> >___
> >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
>



-- 
Ryan B Hayward
Professor and Director (Outreach+Diversity)
Computing Science,  UAlberta
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Lucas, Simon M]

In my original post I put a link to
the relevant section of the MacKay 
book that shows exactly how to calculate
the probability of superiority 
assuming the game outcome is modelled as 
a biased coin toss:

http://www.inference.phy.cam.ac.uk/itila/


I was making the point that for this

and for other outcomes of skill-based games
we can do so much more (and as humans we intuitively
DO do so much more) than just look at the event
outcome - and maybe as a community we should do that more
routinely and more quantitatively (e.g.
by analysing the quality of each move / action)

Best wishes,

  Simon



On 30/03/2016, 11:57, "Computer-go on behalf of djhbrown ." 
 wrote:

>Simon wrote: "I was discussing the results with a colleague outside
>of the Game AI area the other day when he raised
>the question (which applies to nearly all sporting events,
>given the small sample size involved)
>of statistical significance - suggesting that on another week
>the result might have been 4-1 to Lee Sedol."
>
>call me naive, but perhaps you could ask your colleague to calculate
>the probability one of side winning 4 games out of 5, and then say
>whether that is within 2 standard deviations of the norm.
>
>his suggestion is complete nonsense, regardless of the small sample
>size.  perhaps you could ask a statistician next time.
>
>-- 
>patient: "whenever i open my mouth, i get a shooting pain in my foot"
>doctor: "fire!"
>http://sites.google.com/site/djhbrown2/home
>https://www.youtube.com/user/djhbrown
>___
>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] Congratulations to AlphaGo (Statistical significance of results)

[djhbrown .]

"do they have positive or negative correlation?"  intriguing question,
Petri.  Intuitively, we might arbitrarily divide the human population
into two groups; one which is discouraged by failure, and the other
which takes the Lady MacBeth attitude of "screw your courage to the
sticking point, and we'll not fail !"  Again, intuitively, we might
expect the two groups to be roughly equal in size, whereupon it
follows that a series of results involving randomly chosen players
would not be markedly different from statistical independence.

these intuitions are corroborated by one experimental study i came
across with Google Scholar's help:
http://www.tandfonline.com/doi/abs/10.1198/016214501753168217

On 30/03/2016, Petri Pitkanen  wrote:
> Since there are only two possible outcomes it pretty much normal. Actually
> binomial which will converge to normal given enough samples
>
> Only thing that cans distort is that consecutive games are not
> independent (which
> is probably the case but do they have positive or negative correlation?)
>
> 2016-03-30 13:06 GMT+03:00 Рождественский Дмитрий :
>
>> I think the error here is that the game outcome is not a normaly
>> distributed random value.
>>
>> Dmitry
>>
>> 30.03.2016, 12:57, "djhbrown ." :
>> > Simon wrote: "I was discussing the results with a colleague outside
>> > of the Game AI area the other day when he raised
>> > the question (which applies to nearly all sporting events,
>> > given the small sample size involved)
>> > of statistical significance - suggesting that on another week
>> > the result might have been 4-1 to Lee Sedol."
>> >
>> > call me naive, but perhaps you could ask your colleague to calculate
>> > the probability one of side winning 4 games out of 5, and then say
>> > whether that is within 2 standard deviations of the norm.
>> >
>> > his suggestion is complete nonsense, regardless of the small sample
>> > size. perhaps you could ask a statistician next time.
>> >
>> > --
>> > patient: "whenever i open my mouth, i get a shooting pain in my foot"
>> > doctor: "fire!"
>> > http://sites.google.com/site/djhbrown2/home
>> > https://www.youtube.com/user/djhbrown
>> > ___
>> > 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
>>
>


-- 
patient: "whenever i open my mouth, i get a shooting pain in my foot"
doctor: "fire!"
http://sites.google.com/site/djhbrown2/home
https://www.youtube.com/user/djhbrown
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Petri Pitkanen]

Since there are only two possible outcomes it pretty much normal. Actually
binomial which will converge to normal given enough samples

Only thing that cans distort is that consecutive games are not
independent (which
is probably the case but do they have positive or negative correlation?)

2016-03-30 13:06 GMT+03:00 Рождественский Дмитрий :

> I think the error here is that the game outcome is not a normaly
> distributed random value.
>
> Dmitry
>
> 30.03.2016, 12:57, "djhbrown ." :
> > Simon wrote: "I was discussing the results with a colleague outside
> > of the Game AI area the other day when he raised
> > the question (which applies to nearly all sporting events,
> > given the small sample size involved)
> > of statistical significance - suggesting that on another week
> > the result might have been 4-1 to Lee Sedol."
> >
> > call me naive, but perhaps you could ask your colleague to calculate
> > the probability one of side winning 4 games out of 5, and then say
> > whether that is within 2 standard deviations of the norm.
> >
> > his suggestion is complete nonsense, regardless of the small sample
> > size. perhaps you could ask a statistician next time.
> >
> > --
> > patient: "whenever i open my mouth, i get a shooting pain in my foot"
> > doctor: "fire!"
> > http://sites.google.com/site/djhbrown2/home
> > https://www.youtube.com/user/djhbrown
> > ___
> > 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] Congratulations to AlphaGo (Statistical significance of results)

[Рождественский Дмитрий]

I think the error here is that the game outcome is not a normaly distributed 
random value.

Dmitry

30.03.2016, 12:57, "djhbrown ." :
> Simon wrote: "I was discussing the results with a colleague outside
> of the Game AI area the other day when he raised
> the question (which applies to nearly all sporting events,
> given the small sample size involved)
> of statistical significance - suggesting that on another week
> the result might have been 4-1 to Lee Sedol."
>
> call me naive, but perhaps you could ask your colleague to calculate
> the probability one of side winning 4 games out of 5, and then say
> whether that is within 2 standard deviations of the norm.
>
> his suggestion is complete nonsense, regardless of the small sample
> size. perhaps you could ask a statistician next time.
>
> --
> patient: "whenever i open my mouth, i get a shooting pain in my foot"
> doctor: "fire!"
> http://sites.google.com/site/djhbrown2/home
> https://www.youtube.com/user/djhbrown
> ___
> 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] Congratulations to AlphaGo (Statistical significance of results)

[Nick Wedd]

On 22 March 2016 at 21:43, Darren Cook  wrote:

< snip >

>
> C'mon DeepMind, put that same version on KGS, set to only play 9p
> players, with the same time controls, and let's get 40 games to give it
> a proper ranking. (If 5 games against Lee Sedol are useful, 40 games
> against a range of players with little to lose, who are systematically
> trying to find its weaknesses, are going to be amazing.)


I don't think DeepMind's real objective was to create a world Go champion.
I think it was to build an engine that could learn to perform difficult
intellectual tasks better than any human; and they chose Go for their first
test because there was a clear objective measure of success.  If I am
right, we won't see much more of their "Go engine", instead they will
direct their resources to training their general-purpose engine to do other
more useful things.

Nick
-- 
Nick Wedd  mapr...@gmail.com
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Robert Jasiek]

On 23.03.2016 15:32, Petr Baudis wrote:

these are beautiful posts.

https://massgoblog.wordpress.com/2016/03/11/lee-sedols-strategy-and-alphagos-weakness/


Before you become too excited, also read my comments on the commentary:
http://www.lifein19x19.com/forum/viewtopic.php?p=200539#p200539

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

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Petr Baudis]

  Thank you, these are beautiful posts.  I enjoyed very much reading
a writeup by Go professional who also took the effort to understand the
principles behind MCTS programs as well as develop a basic intution of
the gameplay artifacts, strengths and weaknesses of MCTS.  It also
nicely describes the reason and consequences for Lee Sedol's different
approaches during the match.

  I think these are really great posts for Go programmers to share with
their Go-playing friends if they are curious about AlphaGo's strength
and what went on in these games!

On Tue, Mar 22, 2016 at 06:26:45PM -0400, Chun Sun wrote:
> FYI. We have translated 3 posts by Li Zhe 6p into English.
> 
> https://massgoblog.wordpress.com/2016/03/11/lee-sedols-strategy-and-alphagos-weakness/
> https://massgoblog.wordpress.com/2016/03/11/game-2-a-nobody-could-have-done-a-better-job-than-lee-sedol/
> https://massgoblog.wordpress.com/2016/03/15/before-game-5/
> 
> These may provide a slightly different perspective than many other pros.
> 
> 
> On Tue, Mar 22, 2016 at 6:21 PM, Darren Cook  wrote:
> 
> > > ...
> > > Pro players who are not familiar with MCTS bot behavior will not see
> > this.
> >
> > I stand by this:
> >
> > >> If you want to argue that "their opinion" was wrong because they don't
> > >> understand the game at the level AlphaGo was playing at, then you can't
> > >> use their opinion in a positive way either.
> >
> > Darren
> >
> > ___
> > 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


-- 
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Chun Sun]

FYI. We have translated 3 posts by Li Zhe 6p into English.

https://massgoblog.wordpress.com/2016/03/11/lee-sedols-strategy-and-alphagos-weakness/
https://massgoblog.wordpress.com/2016/03/11/game-2-a-nobody-could-have-done-a-better-job-than-lee-sedol/
https://massgoblog.wordpress.com/2016/03/15/before-game-5/

These may provide a slightly different perspective than many other pros.


On Tue, Mar 22, 2016 at 6:21 PM, Darren Cook  wrote:

> > ...
> > Pro players who are not familiar with MCTS bot behavior will not see
> this.
>
> I stand by this:
>
> >> If you want to argue that "their opinion" was wrong because they don't
> >> understand the game at the level AlphaGo was playing at, then you can't
> >> use their opinion in a positive way either.
>
> Darren
>
> ___
> 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] Congratulations to AlphaGo (Statistical significance of results)

[Darren Cook]

> ...
> Pro players who are not familiar with MCTS bot behavior will not see this.

I stand by this:

>> If you want to argue that "their opinion" was wrong because they don't
>> understand the game at the level AlphaGo was playing at, then you can't
>> use their opinion in a positive way either.

Darren

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

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Ingo Althöfer]

Hi Darren,

"Darren Cook" 
> ... But, there were also numerous moves where
> the 9-dan pros said, that in *their* opinion, the moves were weak/wrong.
> E.g. wasting ko threats for no reason. Moves even a 1p would never make.
>
> If you want to argue that "their opinion" was wrong because they don't
> understand the game at the level AlphaGo was playing at, then you can't
> use their opinion in a positive way either.

For these situations there is a very natural explanation, at least for
computer go insiders: The seemingly weak moves happened bcause AlphaGo simply 
tried to maximize the winning probability and not the expected score. 

Pro players who are not familiar with MCTS bot behavior will not see this.


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

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Ingo Althöfer]

"Lucas, Simon M" 
> my point is that I *think* we can say more (for example
> by not treating the outcome as a black-box event,
> but by appreciating the skill of the individual moves)


* Human professional players were full of praise for some of
AlphaGo's moves, for instance move 37 in game 2.


* Although the bots Zen and Crazy are not independent witnesses:
they both saw AlphaGo on the winning path early on in all four won games.


* The score order 1-0, 2-0, 3-0, 3-1, 4-1 with the Sedol win in the
second match half is an indicator that he may have learned something
about the opponent during the early games. 

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

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Darren Cook]

> ... we witnessed hundreds of moves vetted by 9dan players, especially
> Michael Redmond's, where each move was vetted. 

This is a promising approach. But, there were also numerous moves where
the 9-dan pros said, that in *their* opinion, the moves were weak/wrong.
E.g. wasting ko threats for no reason. Moves even a 1p would never make.

If you want to argue that "their opinion" was wrong because they don't
understand the game at the level AlphaGo was playing at, then you can't
use their opinion in a positive way either.

> nearly all sporting events, given the small sample size involved) of
> statistical significance - suggesting that on another week the result
> might have been 4-1 to Lee Sedol.

If his 2nd game had been the one where he created vaguely alive/dead
groups and forced a mistake, and given that we were told the computer
was not being changed during the match, he might have created 2 wins
just by playing exactly the same.

And if he had known this in advance he might then have realized that
creating multiple weak groups and some large complicated kos are the way
to beat it, and so it could well have gone 4-1 to Lee Sedol in "another
week".

C'mon DeepMind, put that same version on KGS, set to only play 9p
players, with the same time controls, and let's get 40 games to give it
a proper ranking. (If 5 games against Lee Sedol are useful, 40 games
against a range of players with little to lose, who are systematically
trying to find its weaknesses, are going to be amazing.)

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

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[uurtamo .]

This is somewhat moot - if any moves had been significantly and obviously
weak to any observers, the results wouldn't have been 4-1.

I.e. One bad move out of 5 games would give roughly the same strength
information as one loss out of 5 games; consider that the kibitzing was
being done in real time.

s.
On Mar 22, 2016 11:08 AM, "Jim O'Flaherty" 
wrote:

> I think you are reinforcing Simon's original point; i.e. using a more fine
> grained approach to statically approximate AlphaGo's ELO where fine grained
> is degree of vetting per move and/or a series of moves. That is a
> substantially larger sample size and each sample will have a pretty high
> degree of quality (given the vetting is being done by top level
> professionals).
> On Mar 22, 2016 1:04 PM, "Jeffrey Greenberg" 
> wrote:
>
>> Given the minimal sample size, bothering over this question won't amount
>> to much. I think the proper response is that no one thought we'd see this
>> level of play at this point in our AI efforts and point to the fact that we
>> witnessed hundreds of moves vetted by 9dan players, especially Michael
>> Redmond's, where each move was vetted. In other words "was the level of
>> play very high?" versus the question "have we beat all humans". The answer
>> is more or less, yes.
>>
>> On Tuesday, March 22, 2016, Lucas, Simon M  wrote:
>>
>>> Hi all,
>>>
>>> I was discussing the results with a colleague outside
>>> of the Game AI area the other day when he raised
>>> the question (which applies to nearly all sporting events,
>>> given the small sample size involved)
>>> of statistical significance - suggesting that on another week
>>> the result might have been 4-1 to Lee Sedol.
>>>
>>> I pointed out that in games of skill there's much more to judge than
>>> just the final
>>> outcome of each game, but wondered if anyone had any better (or worse :)
>>> arguments - or had even engaged in the same type of
>>> conversation.
>>>
>>> With AlphaGo winning 4 games to 1, from a simplistic
>>> stats point of view (with the prior assumption of a fair
>>> coin toss) you'd not be able to claim much statistical
>>> significance, yet most (me included) believe that
>>> AlphaGo is a genuinely better Go player than Lee Sedol.
>>>
>>> From a stats viewpoint you can use this approach:
>>> http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
>>> (see section 3.2 on page 51)
>>>
>>> but given even priors it won't tell you much.
>>>
>>> Anyone know any good references for refuting this
>>> type of argument - the fact is of course that a game of Go
>>> is nothing like a coin toss.  Games of skill tend to base their
>>> outcomes on the result of many (in the case of Go many hundreds of)
>>> individual actions.
>>>
>>> Best wishes,
>>>
>>>   Simon
>>>
>>>
>>> ___
>>> 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] Congratulations to AlphaGo (Statistical significance of results)

[Jim O'Flaherty]

I think you are reinforcing Simon's original point; i.e. using a more fine
grained approach to statically approximate AlphaGo's ELO where fine grained
is degree of vetting per move and/or a series of moves. That is a
substantially larger sample size and each sample will have a pretty high
degree of quality (given the vetting is being done by top level
professionals).
On Mar 22, 2016 1:04 PM, "Jeffrey Greenberg"  wrote:

> Given the minimal sample size, bothering over this question won't amount
> to much. I think the proper response is that no one thought we'd see this
> level of play at this point in our AI efforts and point to the fact that we
> witnessed hundreds of moves vetted by 9dan players, especially Michael
> Redmond's, where each move was vetted. In other words "was the level of
> play very high?" versus the question "have we beat all humans". The answer
> is more or less, yes.
>
> On Tuesday, March 22, 2016, Lucas, Simon M  wrote:
>
>> Hi all,
>>
>> I was discussing the results with a colleague outside
>> of the Game AI area the other day when he raised
>> the question (which applies to nearly all sporting events,
>> given the small sample size involved)
>> of statistical significance - suggesting that on another week
>> the result might have been 4-1 to Lee Sedol.
>>
>> I pointed out that in games of skill there's much more to judge than just
>> the final
>> outcome of each game, but wondered if anyone had any better (or worse :)
>> arguments - or had even engaged in the same type of
>> conversation.
>>
>> With AlphaGo winning 4 games to 1, from a simplistic
>> stats point of view (with the prior assumption of a fair
>> coin toss) you'd not be able to claim much statistical
>> significance, yet most (me included) believe that
>> AlphaGo is a genuinely better Go player than Lee Sedol.
>>
>> From a stats viewpoint you can use this approach:
>> http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
>> (see section 3.2 on page 51)
>>
>> but given even priors it won't tell you much.
>>
>> Anyone know any good references for refuting this
>> type of argument - the fact is of course that a game of Go
>> is nothing like a coin toss.  Games of skill tend to base their
>> outcomes on the result of many (in the case of Go many hundreds of)
>> individual actions.
>>
>> Best wishes,
>>
>>   Simon
>>
>>
>> ___
>> 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] Congratulations to AlphaGo (Statistical significance of results)

[Thomas Wolf]

I am sorry, but I think this discussion is a bit pointless.
While I write these 3 lines and you read them, AlphGo got 20 ELO 
points stronger. :-)


Thomas

On Tue, 22 Mar 2016, Lucas, Simon M wrote:



Still an interesting question is how one could make

more powerful inferences by observing the skill of

the players in each action they take rather than just

the final outcome of each game.

 

If you saw me play a single game of tennis against Federer

you’d have no doubt as to which way the next 100 games would go.

 

From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Álvaro Begué
Sent: 22 March 2016 17:21
To: computer-go <computer-go@computer-go.org>
Subject: Re: [Computer-go] Congratulations to AlphaGo (Statistical significance 
of results)

 

A very simple-minded analysis is that, if the null hypothesis is that AlphaGo 
and Lee Sedol are
equally strong, AlphaGo would do as well as we observed or better 15.625% of 
the time. That's a
p-value that even social scientists don't get excited about. :)

Álvaro.

 

On Tue, Mar 22, 2016 at 12:48 PM, Jason House <jason.james.ho...@gmail.com> 
wrote:

  Statistical significance requires a null hypothesis... I think it's 
probably easiest to
  ask the question of if I assume an ELO difference of x, how likely it's a 
4-1 result?
  Turns out that 220 to 270 ELO has a 41% chance of that result.
  >= 10% is -50 to 670 ELO
  >= 1% is -250 to 1190 ELO
  My numbers may be slightly off from eyeballing things in a simple excel 
sheet. The idea
  and ranges should be clear though

  On Mar 22, 2016 12:00 PM, "Lucas, Simon M" <s...@essex.ac.uk> wrote:

Hi all,

I was discussing the results with a colleague outside
of the Game AI area the other day when he raised
the question (which applies to nearly all sporting events,
given the small sample size involved)
of statistical significance - suggesting that on another week
the result might have been 4-1 to Lee Sedol.

I pointed out that in games of skill there's much more to judge 
than just the
final
outcome of each game, but wondered if anyone had any better (or 
worse :)
arguments - or had even engaged in the same type of
conversation.

With AlphaGo winning 4 games to 1, from a simplistic
stats point of view (with the prior assumption of a fair
coin toss) you'd not be able to claim much statistical
significance, yet most (me included) believe that
AlphaGo is a genuinely better Go player than Lee Sedol.

From a stats viewpoint you can use this approach:
http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
(see section 3.2 on page 51)

but given even priors it won't tell you much.

Anyone know any good references for refuting this
type of argument - the fact is of course that a game of Go
is nothing like a coin toss.  Games of skill tend to base their
outcomes on the result of many (in the case of Go many hundreds of)
individual actions.

Best wishes,

  Simon


___
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] Congratulations to AlphaGo (Statistical significance of results)

[Jeffrey Greenberg]

Given the minimal sample size, bothering over this question won't amount to
much. I think the proper response is that no one thought we'd see this
level of play at this point in our AI efforts and point to the fact that we
witnessed hundreds of moves vetted by 9dan players, especially Michael
Redmond's, where each move was vetted. In other words "was the level of
play very high?" versus the question "have we beat all humans". The answer
is more or less, yes.

On Tuesday, March 22, 2016, Lucas, Simon M  wrote:

> Hi all,
>
> I was discussing the results with a colleague outside
> of the Game AI area the other day when he raised
> the question (which applies to nearly all sporting events,
> given the small sample size involved)
> of statistical significance - suggesting that on another week
> the result might have been 4-1 to Lee Sedol.
>
> I pointed out that in games of skill there's much more to judge than just
> the final
> outcome of each game, but wondered if anyone had any better (or worse :)
> arguments - or had even engaged in the same type of
> conversation.
>
> With AlphaGo winning 4 games to 1, from a simplistic
> stats point of view (with the prior assumption of a fair
> coin toss) you'd not be able to claim much statistical
> significance, yet most (me included) believe that
> AlphaGo is a genuinely better Go player than Lee Sedol.
>
> From a stats viewpoint you can use this approach:
> http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
> (see section 3.2 on page 51)
>
> but given even priors it won't tell you much.
>
> Anyone know any good references for refuting this
> type of argument - the fact is of course that a game of Go
> is nothing like a coin toss.  Games of skill tend to base their
> outcomes on the result of many (in the case of Go many hundreds of)
> individual actions.
>
> Best wishes,
>
>   Simon
>
>
> ___
> 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] Congratulations to AlphaGo (Statistical significance of results)

[Ryan Hayward]

another interesting question is to judge the bot's strength
by watching the facial gestures and body language of Lee Sedol
with each move...

On Tue, Mar 22, 2016 at 11:46 AM, Álvaro Begué 
wrote:

>
>
> On Tue, Mar 22, 2016 at 1:40 PM, Nick Wedd  wrote:
>
>> On 22 March 2016 at 17:20, Álvaro Begué  wrote:
>>
>>> A very simple-minded analysis is that, if the null hypothesis is that
>>> AlphaGo and Lee Sedol are equally strong, AlphaGo would do as well as we
>>> observed or better 15.625% of the time. That's a p-value that even social
>>> scientists don't get excited about. :)
>>>
>>>
>> "For "as well ... or better", I make it 18.75%.
>>
>
> I obviously can't count. :)
>
> Thanks for the correction.
>
> Álvaro.
>
>
>
>
>>
>> Nick
>>
>>
>>
>>> Álvaro.
>>>
>>>
>>> On Tue, Mar 22, 2016 at 12:48 PM, Jason House <
>>> jason.james.ho...@gmail.com> wrote:
>>>
 Statistical significance requires a null hypothesis... I think it's
 probably easiest to ask the question of if I assume an ELO difference of x,
 how likely it's a 4-1 result?
 Turns out that 220 to 270 ELO has a 41% chance of that result.
 >= 10% is -50 to 670 ELO
 >= 1% is -250 to 1190 ELO
 My numbers may be slightly off from eyeballing things in a simple excel
 sheet. The idea and ranges should be clear though
 On Mar 22, 2016 12:00 PM, "Lucas, Simon M"  wrote:

> Hi all,
>
> I was discussing the results with a colleague outside
> of the Game AI area the other day when he raised
> the question (which applies to nearly all sporting events,
> given the small sample size involved)
> of statistical significance - suggesting that on another week
> the result might have been 4-1 to Lee Sedol.
>
> I pointed out that in games of skill there's much more to judge than
> just the final
> outcome of each game, but wondered if anyone had any better (or worse
> :)
> arguments - or had even engaged in the same type of
> conversation.
>
> With AlphaGo winning 4 games to 1, from a simplistic
> stats point of view (with the prior assumption of a fair
> coin toss) you'd not be able to claim much statistical
> significance, yet most (me included) believe that
> AlphaGo is a genuinely better Go player than Lee Sedol.
>
> From a stats viewpoint you can use this approach:
> http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
> (see section 3.2 on page 51)
>
> but given even priors it won't tell you much.
>
> Anyone know any good references for refuting this
> type of argument - the fact is of course that a game of Go
> is nothing like a coin toss.  Games of skill tend to base their
> outcomes on the result of many (in the case of Go many hundreds of)
> individual actions.
>
> Best wishes,
>
>   Simon
>
>
> ___
> 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
>>>
>>
>>
>>
>> --
>> Nick Wedd  mapr...@gmail.com
>>
>> ___
>> 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
>



-- 
Ryan B Hayward
Professor and Director (Outreach+Diversity)
Computing Science,  UAlberta
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Álvaro Begué]

On Tue, Mar 22, 2016 at 1:40 PM, Nick Wedd  wrote:

> On 22 March 2016 at 17:20, Álvaro Begué  wrote:
>
>> A very simple-minded analysis is that, if the null hypothesis is that
>> AlphaGo and Lee Sedol are equally strong, AlphaGo would do as well as we
>> observed or better 15.625% of the time. That's a p-value that even social
>> scientists don't get excited about. :)
>>
>>
> "For "as well ... or better", I make it 18.75%.
>

I obviously can't count. :)

Thanks for the correction.

Álvaro.




>
> Nick
>
>
>
>> Álvaro.
>>
>>
>> On Tue, Mar 22, 2016 at 12:48 PM, Jason House <
>> jason.james.ho...@gmail.com> wrote:
>>
>>> Statistical significance requires a null hypothesis... I think it's
>>> probably easiest to ask the question of if I assume an ELO difference of x,
>>> how likely it's a 4-1 result?
>>> Turns out that 220 to 270 ELO has a 41% chance of that result.
>>> >= 10% is -50 to 670 ELO
>>> >= 1% is -250 to 1190 ELO
>>> My numbers may be slightly off from eyeballing things in a simple excel
>>> sheet. The idea and ranges should be clear though
>>> On Mar 22, 2016 12:00 PM, "Lucas, Simon M"  wrote:
>>>
 Hi all,

 I was discussing the results with a colleague outside
 of the Game AI area the other day when he raised
 the question (which applies to nearly all sporting events,
 given the small sample size involved)
 of statistical significance - suggesting that on another week
 the result might have been 4-1 to Lee Sedol.

 I pointed out that in games of skill there's much more to judge than
 just the final
 outcome of each game, but wondered if anyone had any better (or worse :)
 arguments - or had even engaged in the same type of
 conversation.

 With AlphaGo winning 4 games to 1, from a simplistic
 stats point of view (with the prior assumption of a fair
 coin toss) you'd not be able to claim much statistical
 significance, yet most (me included) believe that
 AlphaGo is a genuinely better Go player than Lee Sedol.

 From a stats viewpoint you can use this approach:
 http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
 (see section 3.2 on page 51)

 but given even priors it won't tell you much.

 Anyone know any good references for refuting this
 type of argument - the fact is of course that a game of Go
 is nothing like a coin toss.  Games of skill tend to base their
 outcomes on the result of many (in the case of Go many hundreds of)
 individual actions.

 Best wishes,

   Simon


 ___
 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
>>
>
>
>
> --
> Nick Wedd  mapr...@gmail.com
>
> ___
> 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] Congratulations to AlphaGo (Statistical significance of results)

[Lucas, Simon M]

Still an interesting question is how one could make
more powerful inferences by observing the skill of
the players in each action they take rather than just
the final outcome of each game.

If you saw me play a single game of tennis against Federer
you’d have no doubt as to which way the next 100 games would go.

From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Álvaro Begué
Sent: 22 March 2016 17:21
To: computer-go <computer-go@computer-go.org>
Subject: Re: [Computer-go] Congratulations to AlphaGo (Statistical significance 
of results)

A very simple-minded analysis is that, if the null hypothesis is that AlphaGo 
and Lee Sedol are equally strong, AlphaGo would do as well as we observed or 
better 15.625% of the time. That's a p-value that even social scientists don't 
get excited about. :)

Álvaro.

On Tue, Mar 22, 2016 at 12:48 PM, Jason House 
<jason.james.ho...@gmail.com<mailto:jason.james.ho...@gmail.com>> wrote:

Statistical significance requires a null hypothesis... I think it's probably 
easiest to ask the question of if I assume an ELO difference of x, how likely 
it's a 4-1 result?
Turns out that 220 to 270 ELO has a 41% chance of that result.
>= 10% is -50 to 670 ELO
>= 1% is -250 to 1190 ELO
My numbers may be slightly off from eyeballing things in a simple excel sheet. 
The idea and ranges should be clear though
On Mar 22, 2016 12:00 PM, "Lucas, Simon M" 
<s...@essex.ac.uk<mailto:s...@essex.ac.uk>> wrote:
Hi all,

I was discussing the results with a colleague outside
of the Game AI area the other day when he raised
the question (which applies to nearly all sporting events,
given the small sample size involved)
of statistical significance - suggesting that on another week
the result might have been 4-1 to Lee Sedol.

I pointed out that in games of skill there's much more to judge than just the 
final
outcome of each game, but wondered if anyone had any better (or worse :)
arguments - or had even engaged in the same type of
conversation.

With AlphaGo winning 4 games to 1, from a simplistic
stats point of view (with the prior assumption of a fair
coin toss) you'd not be able to claim much statistical
significance, yet most (me included) believe that
AlphaGo is a genuinely better Go player than Lee Sedol.

From a stats viewpoint you can use this approach:
http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
(see section 3.2 on page 51)

but given even priors it won't tell you much.

Anyone know any good references for refuting this
type of argument - the fact is of course that a game of Go
is nothing like a coin toss.  Games of skill tend to base their
outcomes on the result of many (in the case of Go many hundreds of)
individual actions.

Best wishes,

  Simon


___
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<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

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Álvaro Begué]

A very simple-minded analysis is that, if the null hypothesis is that
AlphaGo and Lee Sedol are equally strong, AlphaGo would do as well as we
observed or better 15.625% of the time. That's a p-value that even social
scientists don't get excited about. :)

Álvaro.


On Tue, Mar 22, 2016 at 12:48 PM, Jason House 
wrote:

> Statistical significance requires a null hypothesis... I think it's
> probably easiest to ask the question of if I assume an ELO difference of x,
> how likely it's a 4-1 result?
> Turns out that 220 to 270 ELO has a 41% chance of that result.
> >= 10% is -50 to 670 ELO
> >= 1% is -250 to 1190 ELO
> My numbers may be slightly off from eyeballing things in a simple excel
> sheet. The idea and ranges should be clear though
> On Mar 22, 2016 12:00 PM, "Lucas, Simon M"  wrote:
>
>> Hi all,
>>
>> I was discussing the results with a colleague outside
>> of the Game AI area the other day when he raised
>> the question (which applies to nearly all sporting events,
>> given the small sample size involved)
>> of statistical significance - suggesting that on another week
>> the result might have been 4-1 to Lee Sedol.
>>
>> I pointed out that in games of skill there's much more to judge than just
>> the final
>> outcome of each game, but wondered if anyone had any better (or worse :)
>> arguments - or had even engaged in the same type of
>> conversation.
>>
>> With AlphaGo winning 4 games to 1, from a simplistic
>> stats point of view (with the prior assumption of a fair
>> coin toss) you'd not be able to claim much statistical
>> significance, yet most (me included) believe that
>> AlphaGo is a genuinely better Go player than Lee Sedol.
>>
>> From a stats viewpoint you can use this approach:
>> http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
>> (see section 3.2 on page 51)
>>
>> but given even priors it won't tell you much.
>>
>> Anyone know any good references for refuting this
>> type of argument - the fact is of course that a game of Go
>> is nothing like a coin toss.  Games of skill tend to base their
>> outcomes on the result of many (in the case of Go many hundreds of)
>> individual actions.
>>
>> Best wishes,
>>
>>   Simon
>>
>>
>> ___
>> 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] Congratulations to AlphaGo (Statistical significance of results)

[Lucas, Simon M]

my point is that I *think* we can say more (for example
by not treating the outcome as a black-box event,
but by appreciating the skill of the individual moves)

From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
uurtamo .
Sent: 22 March 2016 16:25
To: computer-go <computer-go@computer-go.org>
Subject: Re: [Computer-go] Congratulations to AlphaGo (Statistical significance 
of results)


> I'm not sure if we can say with certainty that AlphaGo is significantly
> better Go player than Lee Sedol at this point.  What we can say with
> certainty is that AlphaGo is in the same ballpark and at least roughly
> as strong as Lee Sedol.  To me, that's enough to be really huge on its
> own accord!

Agreed, and exactly what I'm telling my friends who have asked the same 
question.

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

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[Petr Baudis]

On Tue, Mar 22, 2016 at 04:00:41PM +, Lucas, Simon M wrote:
> With AlphaGo winning 4 games to 1, from a simplistic
> stats point of view (with the prior assumption of a fair
> coin toss) you'd not be able to claim much statistical 
> significance, yet most (me included) believe that
> AlphaGo is a genuinely better Go player than Lee Sedol.
> 
> From a stats viewpoint you can use this approach:
> http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
> (see section 3.2 on page 51)
> 
> but given even priors it won't tell you much.

What complicates things further is that the coin distribution is
non-stationary; definitely from the point of the human performance
against a fixed program (how much AlphaGo with its novel RL component
is fixed is of course another matter).  In fact, as anyone watching bots
playing on KGS knows, initially the non-stationarity is actually very
extreme as the human gets "used to" the computer's style and soon are
able to beat even a program that's formally quite stronger than the
human player.  At least that's the case for the weaker programs.

I'm not sure if we can say with certainty that AlphaGo is significantly
better Go player than Lee Sedol at this point.  What we can say with
certainty is that AlphaGo is in the same ballpark and at least roughly
as strong as Lee Sedol.  To me, that's enough to be really huge on its
own accord!

-- 
Petr Baudis
If you have good ideas, good data and fast computers,
you can do almost anything. -- Geoffrey Hinton
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo (Statistical significance of results)

[uurtamo .]

Simon,

There's no argument better than evidence, and no evidence available to us
other than *all* of the games that alphago has played publicly.

Among two humans, a 4-1 result wouldn't indicate any more or less than this
4-1 result, but we'd already have very strong elo-type information about
both humans because they both would have publicly played hundreds of games
to get to such a match.

I believe alphago played another match earlier in public, correct?  Then we
now have double the evidence, or a slight (50% or so) improvement in our
confidence bounds.

s.
On Mar 22, 2016 9:00 AM, "Lucas, Simon M"  wrote:

> Hi all,
>
> I was discussing the results with a colleague outside
> of the Game AI area the other day when he raised
> the question (which applies to nearly all sporting events,
> given the small sample size involved)
> of statistical significance - suggesting that on another week
> the result might have been 4-1 to Lee Sedol.
>
> I pointed out that in games of skill there's much more to judge than just
> the final
> outcome of each game, but wondered if anyone had any better (or worse :)
> arguments - or had even engaged in the same type of
> conversation.
>
> With AlphaGo winning 4 games to 1, from a simplistic
> stats point of view (with the prior assumption of a fair
> coin toss) you'd not be able to claim much statistical
> significance, yet most (me included) believe that
> AlphaGo is a genuinely better Go player than Lee Sedol.
>
> From a stats viewpoint you can use this approach:
> http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
> (see section 3.2 on page 51)
>
> but given even priors it won't tell you much.
>
> Anyone know any good references for refuting this
> type of argument - the fact is of course that a game of Go
> is nothing like a coin toss.  Games of skill tend to base their
> outcomes on the result of many (in the case of Go many hundreds of)
> individual actions.
>
> Best wishes,
>
>   Simon
>
>
> ___
> 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] Congratulations to AlphaGo (Statistical significance of results)

[Lucas, Simon M]

Hi all,

I was discussing the results with a colleague outside
of the Game AI area the other day when he raised
the question (which applies to nearly all sporting events,
given the small sample size involved)
of statistical significance - suggesting that on another week
the result might have been 4-1 to Lee Sedol.

I pointed out that in games of skill there's much more to judge than just the 
final
outcome of each game, but wondered if anyone had any better (or worse :) 
arguments - or had even engaged in the same type of
conversation.

With AlphaGo winning 4 games to 1, from a simplistic
stats point of view (with the prior assumption of a fair
coin toss) you'd not be able to claim much statistical 
significance, yet most (me included) believe that
AlphaGo is a genuinely better Go player than Lee Sedol.

From a stats viewpoint you can use this approach:
http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
(see section 3.2 on page 51)

but given even priors it won't tell you much.

Anyone know any good references for refuting this
type of argument - the fact is of course that a game of Go
is nothing like a coin toss.  Games of skill tend to base their
outcomes on the result of many (in the case of Go many hundreds of)
individual actions.

Best wishes,

  Simon


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

Re: [Computer-go] Congratulations to AlphaGo

[David Doshay]

Here is a tinyURL link to a panel discussion of things AlphaGo that included:

• Oliver Roeder: Senior writer at FiveThirtyEight. All too human.
• David Doshay: Archivist for the American Go Association, co-creator 
of SlugGo, a Go-playing computer program.
• Matt Ginsberg: Businessman, astrophysicist, creator of a former 
computer bridge champion called GIB and an expert-level AI crossword puzzle 
solver called Dr. Fill. FiveThirtyEight wrote about Matt and his new basketball 
prediction technology in October.
• Andy Okun: President of the American Go Association and a 1 dan Go 
player. He attended the match in Seoul.
• Jonathan Schaeffer: Computer science professor at the University of 
Alberta and the man who solved checkers.
This conversation has been edited for length and clarity.

http://tinyurl.com/jx7ctaw

As with all editing, each of us might have done it differently … at one point I 
am going on about multi-cpu and multitasking without context because they 
edited out the comment I was responding to. But I am pleased with the article 
in total, particularly the headline they chose which I think will resonate with 
the people on this list.

Cheers,
David G Doshay

ddos...@mac.com





> On 21, Mar 2016, at 10:22 AM, Ingo Althöfer <3-hirn-ver...@gmx.de> wrote:
> 
> Helo,
> 
> popular culture is growing around AlphaGo's win. Some pieces are
> nice: others are, let's say, "special":
> 
> Here is the link to a nice Youtube video with an A capella hymnus 
> (31 seconds) on AlphaGo, performed on 9 GPU ;-)
> 
> https://www.youtube.com/watch?v=dh_mfGo183Y
> 
> 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] Congratulations to AlphaGo

[Robert Jasiek]

On 12.03.2016 22:03, Thomas Wolf wrote:

We currently have no measure at all to judge how safe a winor loss is at
any stage of the game.


We have my theory according to my books for assessing the territorial 
and the dynamic aspects (development directions, neutral stones, 
statuses (incl. those of potential invasion groups), options, aji, 
invasions, reductions, (local) potential, influence, thickness, fights) 
of every position. The theory does not provide a single number (such as 
a one-dimensional probability) but judgement need not be one-dimensional 
and can depend on reading to assess particular aspects, such as a status.



The only valid strength indicator would be to gradually increase handicap
stones or komi for the previous loser in a series of games.


Altering komi is much better than altering handicap because komi can be 
adjusted in finer steps and does not artificially restrict strategy a lot.


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

Re: [Computer-go] Congratulations to AlphaGo

[Gonçalo Mendes Ferreira]

The single machine version and the 2000 machine version is apparently a
difference in 150 ELO, so maybe a 32 core instance in Amazon would be
close enough, costing about 1200$ a month. Maybe it's doable, or for a
Tokyo U. or BGA or AGA to set up something like this with Google permission.

On 13/03/2016 00:24, Lukas van de Wiel wrote:
> This would be many thousands of dollars per day. A single game would be
> more than a thousand dollars in total costs.
> I do not think a kickstarter project or so would be successful, as the go
> community is simply not *that* big...
> 
> On Sun, Mar 13, 2016 at 1:17 PM, Gonçalo Mendes Ferreira 
> wrote:
> 
>> It does seem unlikely for DeepMind not to move on to "bigger" things,
>> but maybe the Go community can make some kind of fundraiser to keep an
>> instance of AlphaGo playing 24/7? I think there are some websites for
>> this kind of thing. Someone would be in charge of scheduling time for it
>> to play pros, other programs, and maybe play online on breaks. Just an
>> idea, oh Google overlords that watch all communications.
>>
>> Gonçalo
>>
>> On 13/03/2016 00:06, Lukas van de Wiel wrote:
>>> Oh, I did not say that it would not be beneficial, to AlphaGo, and to the
>>> people playing it, and to the Go community as a whole, but still, it will
>>> have to come from somewhere. Just the electricity bill alone would be
>>> hair-raising.
>>> And the big-scale benefits in prestige and marketing are over, with this
>>> victory.
>>>
>>> It would be cool to build on the works of AlphaGo, and I would like to
>> see
>>> it as much as the next enthusiast, but I doubt the feasibility...
>>>
>>> On Sun, Mar 13, 2016 at 1:01 PM, Thomas Wolf  wrote:
>>>


 On Sat, 12 Mar 2016, Lukas van de Wiel wrote:

 And the hardware available for this tournament was tremendous. It
>> remains
> to be seen whether the hardware and the people
> maintaining it would be available for a longer period. The costs of
>> this
> are not to be underestimated. Who would pay it?
>

 The AlphaGo team would get feedback from testing by players with very
 different ideas/strengths who they would otherwise never get in contact
 with.

 For example, Michael Redmond mentioned repeatedly in the last 3 reviews
 that
 he would love to play AlphaGo to study Go, to find new openings,...



> Lukas
>
> On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda 
> wrote:
>   On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf 
> wrote:
> Having AlphaGo playing exclusively on KGS would be such a
> boost to KGS!
>
>   For sure.
>
> The other Go servers might have their own opinion on that.
>
> Clark
>
>> ___
>> 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] Congratulations to AlphaGo

[Jim O'Flaherty]

I'd expect this achievement by AlphaGo is very similar to when the first
human ran a 4 minute mile. No one had done it prior. However, right after
Roger Bannister did it, suddenly there were people all over the planet
doing it. Roger Bannister essentially made the possibility real, and then
the psychology changed and lots of others made it over the hurdle. AlphaGo
turned the possibility of an AI becoming a 9d into reality.

AlphaGo may have made it to 9d first. However, I expect we will now begin
seeing lots of different successful attempts to accomplish the same thing,
and relatively soon, too. We've already seen several different comments on
this email list of people working furiously to make the same leaps the
AlphaGo team have described creating. The risk on these investments has
been substantially reduced by AlphaGo's unambiguous success. If the chess
world is any sort of guide to how Go AI is going to continue to develop,
then we will see plenty of progress over the next 36 months. I wouldn't be
surprised to hear the Facebook team working on their AI ends up coming in
second to the +9d AI club.


On Sat, Mar 12, 2016 at 6:25 PM, Igor Polyakov 
wrote:

> At this point I don't doubt that the single machine version is
> professional strength which is enough to be used as a tool to analyze
> games...
>
>
> On 2016-03-12 16:24, Lukas van de Wiel wrote:
>
> This would be many thousands of dollars per day. A single game would be
> more than a thousand dollars in total costs.
> I do not think a kickstarter project or so would be successful, as the go
> community is simply not *that* big...
>
> On Sun, Mar 13, 2016 at 1:17 PM, Gonçalo Mendes Ferreira < 
> go...@sapo.pt> wrote:
>
>> It does seem unlikely for DeepMind not to move on to "bigger" things,
>> but maybe the Go community can make some kind of fundraiser to keep an
>> instance of AlphaGo playing 24/7? I think there are some websites for
>> this kind of thing. Someone would be in charge of scheduling time for it
>> to play pros, other programs, and maybe play online on breaks. Just an
>> idea, oh Google overlords that watch all communications.
>>
>> Gonçalo
>>
>> On 13/03/2016 00:06, Lukas van de Wiel wrote:
>> > Oh, I did not say that it would not be beneficial, to AlphaGo, and to
>> the
>> > people playing it, and to the Go community as a whole, but still, it
>> will
>> > have to come from somewhere. Just the electricity bill alone would be
>> > hair-raising.
>> > And the big-scale benefits in prestige and marketing are over, with this
>> > victory.
>> >
>> > It would be cool to build on the works of AlphaGo, and I would like to
>> see
>> > it as much as the next enthusiast, but I doubt the feasibility...
>> >
>> > On Sun, Mar 13, 2016 at 1:01 PM, Thomas Wolf < 
>> tw...@brocku.ca> wrote:
>> >
>> >>
>> >>
>> >> On Sat, 12 Mar 2016, Lukas van de Wiel wrote:
>> >>
>> >> And the hardware available for this tournament was tremendous. It
>> remains
>> >>> to be seen whether the hardware and the people
>> >>> maintaining it would be available for a longer period. The costs of
>> this
>> >>> are not to be underestimated. Who would pay it?
>> >>>
>> >>
>> >> The AlphaGo team would get feedback from testing by players with very
>> >> different ideas/strengths who they would otherwise never get in contact
>> >> with.
>> >>
>> >> For example, Michael Redmond mentioned repeatedly in the last 3 reviews
>> >> that
>> >> he would love to play AlphaGo to study Go, to find new openings,...
>> >>
>> >>
>> >>
>> >>> Lukas
>> >>>
>> >>> On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda > >
>> >>> wrote:
>> >>>   On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf 
>> >>> wrote:
>> >>> Having AlphaGo playing exclusively on KGS would be such a
>> >>> boost to KGS!
>> >>>
>> >>>   For sure.
>> >>>
>> >>> The other Go servers might have their own opinion on that.
>> >>>
>> >>> Clark
>> >>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
>
>
> ___
> Computer-go mailing 
> listComputer-go@computer-go.orghttp://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] Congratulations to AlphaGo

[Igor Polyakov]

At this point I don't doubt that the single machine version is 
professional strength which is enough to be used as a tool to analyze 
games...


On 2016-03-12 16:24, Lukas van de Wiel wrote:
This would be many thousands of dollars per day. A single game would 
be more than a thousand dollars in total costs.
I do not think a kickstarter project or so would be successful, as the 
go community is simply not *that* big...


On Sun, Mar 13, 2016 at 1:17 PM, Gonçalo Mendes Ferreira 
> wrote:


It does seem unlikely for DeepMind not to move on to "bigger" things,
but maybe the Go community can make some kind of fundraiser to keep an
instance of AlphaGo playing 24/7? I think there are some websites for
this kind of thing. Someone would be in charge of scheduling time
for it
to play pros, other programs, and maybe play online on breaks. Just an
idea, oh Google overlords that watch all communications.

Gonçalo

On 13/03/2016 00:06, Lukas van de Wiel wrote:
> Oh, I did not say that it would not be beneficial, to AlphaGo,
and to the
> people playing it, and to the Go community as a whole, but
still, it will
> have to come from somewhere. Just the electricity bill alone
would be
> hair-raising.
> And the big-scale benefits in prestige and marketing are over,
with this
> victory.
>
> It would be cool to build on the works of AlphaGo, and I would
like to see
> it as much as the next enthusiast, but I doubt the feasibility...
>
> On Sun, Mar 13, 2016 at 1:01 PM, Thomas Wolf > wrote:
>
>>
>>
>> On Sat, 12 Mar 2016, Lukas van de Wiel wrote:
>>
>> And the hardware available for this tournament was tremendous.
It remains
>>> to be seen whether the hardware and the people
>>> maintaining it would be available for a longer period. The
costs of this
>>> are not to be underestimated. Who would pay it?
>>>
>>
>> The AlphaGo team would get feedback from testing by players
with very
>> different ideas/strengths who they would otherwise never get in
contact
>> with.
>>
>> For example, Michael Redmond mentioned repeatedly in the last 3
reviews
>> that
>> he would love to play AlphaGo to study Go, to find new openings,...
>>
>>
>>
>>> Lukas
>>>
>>> On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda
>
>>> wrote:
>>>   On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf
>
>>> wrote:
>>> Having AlphaGo playing exclusively on KGS would be
such a
>>> boost to KGS!
>>>
>>>   For sure.
>>>
>>> The other Go servers might have their own opinion on that.
>>>
>>> Clark
>>>
___
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] Congratulations to AlphaGo

[Lukas van de Wiel]

This would be many thousands of dollars per day. A single game would be
more than a thousand dollars in total costs.
I do not think a kickstarter project or so would be successful, as the go
community is simply not *that* big...

On Sun, Mar 13, 2016 at 1:17 PM, Gonçalo Mendes Ferreira 
wrote:

> It does seem unlikely for DeepMind not to move on to "bigger" things,
> but maybe the Go community can make some kind of fundraiser to keep an
> instance of AlphaGo playing 24/7? I think there are some websites for
> this kind of thing. Someone would be in charge of scheduling time for it
> to play pros, other programs, and maybe play online on breaks. Just an
> idea, oh Google overlords that watch all communications.
>
> Gonçalo
>
> On 13/03/2016 00:06, Lukas van de Wiel wrote:
> > Oh, I did not say that it would not be beneficial, to AlphaGo, and to the
> > people playing it, and to the Go community as a whole, but still, it will
> > have to come from somewhere. Just the electricity bill alone would be
> > hair-raising.
> > And the big-scale benefits in prestige and marketing are over, with this
> > victory.
> >
> > It would be cool to build on the works of AlphaGo, and I would like to
> see
> > it as much as the next enthusiast, but I doubt the feasibility...
> >
> > On Sun, Mar 13, 2016 at 1:01 PM, Thomas Wolf  wrote:
> >
> >>
> >>
> >> On Sat, 12 Mar 2016, Lukas van de Wiel wrote:
> >>
> >> And the hardware available for this tournament was tremendous. It
> remains
> >>> to be seen whether the hardware and the people
> >>> maintaining it would be available for a longer period. The costs of
> this
> >>> are not to be underestimated. Who would pay it?
> >>>
> >>
> >> The AlphaGo team would get feedback from testing by players with very
> >> different ideas/strengths who they would otherwise never get in contact
> >> with.
> >>
> >> For example, Michael Redmond mentioned repeatedly in the last 3 reviews
> >> that
> >> he would love to play AlphaGo to study Go, to find new openings,...
> >>
> >>
> >>
> >>> Lukas
> >>>
> >>> On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda 
> >>> wrote:
> >>>   On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf 
> >>> wrote:
> >>> Having AlphaGo playing exclusively on KGS would be such a
> >>> boost to KGS!
> >>>
> >>>   For sure.
> >>>
> >>> The other Go servers might have their own opinion on that.
> >>>
> >>> Clark
> >>>
> ___
> 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] Congratulations to AlphaGo

[Gonçalo Mendes Ferreira]

It does seem unlikely for DeepMind not to move on to "bigger" things,
but maybe the Go community can make some kind of fundraiser to keep an
instance of AlphaGo playing 24/7? I think there are some websites for
this kind of thing. Someone would be in charge of scheduling time for it
to play pros, other programs, and maybe play online on breaks. Just an
idea, oh Google overlords that watch all communications.

Gonçalo

On 13/03/2016 00:06, Lukas van de Wiel wrote:
> Oh, I did not say that it would not be beneficial, to AlphaGo, and to the
> people playing it, and to the Go community as a whole, but still, it will
> have to come from somewhere. Just the electricity bill alone would be
> hair-raising.
> And the big-scale benefits in prestige and marketing are over, with this
> victory.
> 
> It would be cool to build on the works of AlphaGo, and I would like to see
> it as much as the next enthusiast, but I doubt the feasibility...
> 
> On Sun, Mar 13, 2016 at 1:01 PM, Thomas Wolf  wrote:
> 
>>
>>
>> On Sat, 12 Mar 2016, Lukas van de Wiel wrote:
>>
>> And the hardware available for this tournament was tremendous. It remains
>>> to be seen whether the hardware and the people
>>> maintaining it would be available for a longer period. The costs of this
>>> are not to be underestimated. Who would pay it?
>>>
>>
>> The AlphaGo team would get feedback from testing by players with very
>> different ideas/strengths who they would otherwise never get in contact
>> with.
>>
>> For example, Michael Redmond mentioned repeatedly in the last 3 reviews
>> that
>> he would love to play AlphaGo to study Go, to find new openings,...
>>
>>
>>
>>> Lukas
>>>
>>> On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda 
>>> wrote:
>>>   On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf 
>>> wrote:
>>> Having AlphaGo playing exclusively on KGS would be such a
>>> boost to KGS!
>>>
>>>   For sure.
>>>
>>> The other Go servers might have their own opinion on that.
>>>
>>> Clark
>>>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo

[Lukas van de Wiel]

Oh, I did not say that it would not be beneficial, to AlphaGo, and to the
people playing it, and to the Go community as a whole, but still, it will
have to come from somewhere. Just the electricity bill alone would be
hair-raising.
And the big-scale benefits in prestige and marketing are over, with this
victory.

It would be cool to build on the works of AlphaGo, and I would like to see
it as much as the next enthusiast, but I doubt the feasibility...

On Sun, Mar 13, 2016 at 1:01 PM, Thomas Wolf  wrote:

>
>
> On Sat, 12 Mar 2016, Lukas van de Wiel wrote:
>
> And the hardware available for this tournament was tremendous. It remains
>> to be seen whether the hardware and the people
>> maintaining it would be available for a longer period. The costs of this
>> are not to be underestimated. Who would pay it?
>>
>
> The AlphaGo team would get feedback from testing by players with very
> different ideas/strengths who they would otherwise never get in contact
> with.
>
> For example, Michael Redmond mentioned repeatedly in the last 3 reviews
> that
> he would love to play AlphaGo to study Go, to find new openings,...
>
>
>
>> Lukas
>>
>> On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda 
>> wrote:
>>   On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf 
>> wrote:
>> Having AlphaGo playing exclusively on KGS would be such a
>> boost to KGS!
>>
>>   For sure.
>>
>> The other Go servers might have their own opinion on that.
>>
>> Clark
>>
>> ___
>> 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] Congratulations to AlphaGo

[Thomas Wolf]

On Sat, 12 Mar 2016, Lukas van de Wiel wrote:


And the hardware available for this tournament was tremendous. It remains to be 
seen whether the hardware and the people
maintaining it would be available for a longer period. The costs of this are 
not to be underestimated. Who would pay it?


The AlphaGo team would get feedback from testing by players with very
different ideas/strengths who they would otherwise never get in contact with.

For example, Michael Redmond mentioned repeatedly in the last 3 reviews that
he would love to play AlphaGo to study Go, to find new openings,...



Lukas

On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda  wrote:
  On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf  wrote:
Having AlphaGo playing exclusively on KGS would be such a boost to 
KGS!

  For sure.

The other Go servers might have their own opinion on that.

Clark 

___
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] Congratulations to AlphaGo

[Lukas van de Wiel]

And the hardware available for this tournament was tremendous. It remains
to be seen whether the hardware and the people maintaining it would be
available for a longer period. The costs of this are not to be
underestimated. Who would pay it?

Lukas

On Sun, Mar 13, 2016 at 12:20 PM, Clark B. Wierda 
wrote:

> On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf  wrote:
>
>> Having AlphaGo playing exclusively on KGS would be such a boost to KGS!
>>
>> For sure.
>
> The other Go servers might have their own opinion on that.
>
> Clark
>
> ___
> 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] Congratulations to AlphaGo

[Clark B. Wierda]

On Sat, Mar 12, 2016 at 5:05 PM, Thomas Wolf  wrote:

> Having AlphaGo playing exclusively on KGS would be such a boost to KGS!
>
> For sure.

The other Go servers might have their own opinion on that.

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

Re: [Computer-go] Congratulations to AlphaGo

[Thomas Wolf]

Having AlphaGo playing exclusively on KGS would be such a boost to KGS!

On Sat, 12 Mar 2016, Brian Sheppard wrote:



Play on KGS. Pros can be anonymous, and test themselves and AlphaGo at the same 
time. :-)

 

From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of Jim 
O'Flaherty
Sent: Saturday, March 12, 2016 4:56 PM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] Congratulations to AlphaGo

 

I think you're correct, Thomas. The challenge is going to be getting ANY 
professional to be the one who
"takes handicap stones" for the first time in years. The possible "shame" of 
doing so is what will make
it messy.

 

Once someone does take that step, though, I think it is only a matter of time 
before the rating of
humans will be made a subordinate rating relative to the "objective" rating of 
the AIs, AlphaGo just
being the first. And that has its own psychological challenges as the Go world 
has many decades of
handling ELOs and rankings for humans. So, I don't think change in this area is 
going to be welcomed
anytime soon.

 

 

On Sat, Mar 12, 2016 at 3:03 PM, Thomas Wolf <tw...@brocku.ca> wrote:

  Chris,

  Prompted from a discussion on the computer go email list
  (and my last email today) :

  We currently have no measure at all to judge how safe a winor loss is at 
any
  stage of the game. The measure applied currently of counting territory 
does
  only apply if both players try to maximize territory but not if at least 
one
  player maximizes the chance of winning. (I know, it was mentioned 
already).

  But really, comments like "Player ... is catching up" are pretty 
meaningless
  and are only valid if one explicitly mentions points or territorry, and 
adds
  that this has nothing to do with winning probabilities.

  Even the winning percentages provided by the computer programs themselves 
are
  no real indicator for winninig chances. They are tools to find the best 
move
  and are a statistical measure over several playout sequences based on 
selfplay
  not based on play against that opponent. Equally, winning percentages 
worked
  out by other computer programs are also not adequate (although they are at
  least unbiased) because they do also not use the real opponents to play 
out
  the sequences.

  The only valid strength indicator would be to gradually increase handicap
  stones or komi for the previous loser in a series of games.

  Regards,
  Thomas



  On Sat, 12 Mar 2016, Sorin Gherman wrote:


It is fascinating indeed to try to find how much stronger is AlphaGo
compared to top humans.

Given the fact that it is hard to find the reason why Lee Sedol 
lost, and
that AlphaGo seems to get mysteriously ahead without a clear 
reason, tells
me that the difference is definitely more than one stone handicap, 
maybe 2+
stones, as crazy as it may sound given Lee Sedol's level.

I am pretty sure he will not accept to play with handicap against 
AlphaGo
though. Maybe "younger wolves" like Ke Jie will though and we will 
find out.

On Mar 12, 2016 11:03 AM, "Thomas Wolf" <tw...@brocku.ca> wrote:
      A suggestion for possible future games to be arranged between
      AlphaGo and
      strong players:

      Whoever lost shall be given 1 stone or the equivalent of 1/2
      stone handcap in the
      next game. Games should continue until each side has won at
      least once. This
      way AlphaGo will be forced to demonstrate its full strength 
over
      a whole game
      which we are all too curious to see.

      Thomas

      On Sat, 12 Mar 2016, Aja Huang wrote:

            Thanks all. AlphaGo has won the match against Lee
            Sedol. But there are still 2 games to play.
            Aja

            On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty
            <jim.oflaherty...@gmail.com> wrote:
                  It was exhilerating to witness history being
            made! Awesome!

            On Sat, Mar 12, 2016 at 2:17 AM, David Fotland
            <fotl...@smart-games.com> wrote:

                  Tremendous games by AlphaGo.  Congratulations!

                   

                  From: Computer-go
            [mailto:computer-go-boun...@computer-go.org] On
            Behalf Of Lukas van de Wiel
                  Sent: Saturday, March 12, 2016 12:14 AM
                  To: computer-go@computer-go.org
       

Re: [Computer-go] Congratulations to AlphaGo

[Lukas van de Wiel]

It makes me think that is a very good idea that they did not select a
Japanese professional to play AlphaGo, They tend to be very passionate
about shame (even though there is of course no shame in losing against
AlphaGo) and it might have been... messy...

On Sun, Mar 13, 2016 at 10:55 AM, Jim O'Flaherty  wrote:

> I think you're correct, Thomas. The challenge is going to be getting ANY
> professional to be the one who "takes handicap stones" for the first time
> in years. The possible "shame" of doing so is what will make it messy.
>
> Once someone does take that step, though, I think it is only a matter of
> time before the rating of humans will be made a subordinate rating relative
> to the "objective" rating of the AIs, AlphaGo just being the first. And
> that has its own psychological challenges as the Go world has many decades
> of handling ELOs and rankings for humans. So, I don't think change in this
> area is going to be welcomed anytime soon.
>
>
> On Sat, Mar 12, 2016 at 3:03 PM, Thomas Wolf  wrote:
>
>> Chris,
>>
>> Prompted from a discussion on the computer go email list
>> (and my last email today) :
>>
>> We currently have no measure at all to judge how safe a winor loss is at
>> any
>> stage of the game. The measure applied currently of counting territory
>> does
>> only apply if both players try to maximize territory but not if at least
>> one
>> player maximizes the chance of winning. (I know, it was mentioned
>> already).
>>
>> But really, comments like "Player ... is catching up" are pretty
>> meaningless
>> and are only valid if one explicitly mentions points or territorry, and
>> adds
>> that this has nothing to do with winning probabilities.
>>
>> Even the winning percentages provided by the computer programs themselves
>> are
>> no real indicator for winninig chances. They are tools to find the best
>> move
>> and are a statistical measure over several playout sequences based on
>> selfplay
>> not based on play against that opponent. Equally, winning percentages
>> worked
>> out by other computer programs are also not adequate (although they are at
>> least unbiased) because they do also not use the real opponents to play
>> out
>> the sequences.
>>
>> The only valid strength indicator would be to gradually increase handicap
>> stones or komi for the previous loser in a series of games.
>>
>> Regards,
>> Thomas
>>
>>
>> On Sat, 12 Mar 2016, Sorin Gherman wrote:
>>
>>
>>> It is fascinating indeed to try to find how much stronger is AlphaGo
>>> compared to top humans.
>>>
>>> Given the fact that it is hard to find the reason why Lee Sedol lost, and
>>> that AlphaGo seems to get mysteriously ahead without a clear reason,
>>> tells
>>> me that the difference is definitely more than one stone handicap, maybe
>>> 2+
>>> stones, as crazy as it may sound given Lee Sedol's level.
>>>
>>> I am pretty sure he will not accept to play with handicap against AlphaGo
>>> though. Maybe "younger wolves" like Ke Jie will though and we will find
>>> out.
>>>
>>> On Mar 12, 2016 11:03 AM, "Thomas Wolf"  wrote:
>>>   A suggestion for possible future games to be arranged between
>>>   AlphaGo and
>>>   strong players:
>>>
>>>   Whoever lost shall be given 1 stone or the equivalent of 1/2
>>>   stone handcap in the
>>>   next game. Games should continue until each side has won at
>>>   least once. This
>>>   way AlphaGo will be forced to demonstrate its full strength over
>>>   a whole game
>>>   which we are all too curious to see.
>>>
>>>   Thomas
>>>
>>>   On Sat, 12 Mar 2016, Aja Huang wrote:
>>>
>>> Thanks all. AlphaGo has won the match against Lee
>>> Sedol. But there are still 2 games to play.
>>> Aja
>>>
>>> On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty
>>>  wrote:
>>>   It was exhilerating to witness history being
>>> made! Awesome!
>>>
>>> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland
>>>  wrote:
>>>
>>>   Tremendous games by AlphaGo.  Congratulations!
>>>
>>>
>>>
>>>   From: Computer-go
>>> [mailto:computer-go-boun...@computer-go.org] On
>>> Behalf Of Lukas van de Wiel
>>>   Sent: Saturday, March 12, 2016 12:14 AM
>>>   To: computer-go@computer-go.org
>>>   Subject: [Computer-go] Congratulations to
>>> AlphaGo
>>>
>>>
>>>
>>> Whoa, what a fight! Well fought, and well won!
>>>
>>> Lukas
>>>
>>>
>>> ___
>>> Computer-go mailing list
>>> Computer-go@computer-go.org
>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>>>
>>>
>>> ___

Re: [Computer-go] Congratulations to AlphaGo

[Brian Sheppard]

Play on KGS. Pros can be anonymous, and test themselves and AlphaGo at the same 
time. :-)

 

From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of Jim 
O'Flaherty
Sent: Saturday, March 12, 2016 4:56 PM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] Congratulations to AlphaGo

 

I think you're correct, Thomas. The challenge is going to be getting ANY 
professional to be the one who "takes handicap stones" for the first time in 
years. The possible "shame" of doing so is what will make it messy.

 

Once someone does take that step, though, I think it is only a matter of time 
before the rating of humans will be made a subordinate rating relative to the 
"objective" rating of the AIs, AlphaGo just being the first. And that has its 
own psychological challenges as the Go world has many decades of handling ELOs 
and rankings for humans. So, I don't think change in this area is going to be 
welcomed anytime soon.

 

 

On Sat, Mar 12, 2016 at 3:03 PM, Thomas Wolf <tw...@brocku.ca 
<mailto:tw...@brocku.ca> > wrote:

Chris,

Prompted from a discussion on the computer go email list
(and my last email today) :

We currently have no measure at all to judge how safe a winor loss is at any
stage of the game. The measure applied currently of counting territory does
only apply if both players try to maximize territory but not if at least one
player maximizes the chance of winning. (I know, it was mentioned already).

But really, comments like "Player ... is catching up" are pretty meaningless
and are only valid if one explicitly mentions points or territorry, and adds
that this has nothing to do with winning probabilities.

Even the winning percentages provided by the computer programs themselves are
no real indicator for winninig chances. They are tools to find the best move
and are a statistical measure over several playout sequences based on selfplay
not based on play against that opponent. Equally, winning percentages worked
out by other computer programs are also not adequate (although they are at
least unbiased) because they do also not use the real opponents to play out
the sequences.

The only valid strength indicator would be to gradually increase handicap
stones or komi for the previous loser in a series of games.

Regards,
Thomas



On Sat, 12 Mar 2016, Sorin Gherman wrote:


It is fascinating indeed to try to find how much stronger is AlphaGo
compared to top humans.

Given the fact that it is hard to find the reason why Lee Sedol lost, and
that AlphaGo seems to get mysteriously ahead without a clear reason, tells
me that the difference is definitely more than one stone handicap, maybe 2+
stones, as crazy as it may sound given Lee Sedol's level.

I am pretty sure he will not accept to play with handicap against AlphaGo
though. Maybe "younger wolves" like Ke Jie will though and we will find out.

On Mar 12, 2016 11:03 AM, "Thomas Wolf" <tw...@brocku.ca 
<mailto:tw...@brocku.ca> > wrote:
  A suggestion for possible future games to be arranged between
  AlphaGo and
  strong players:

  Whoever lost shall be given 1 stone or the equivalent of 1/2
  stone handcap in the
  next game. Games should continue until each side has won at
  least once. This
  way AlphaGo will be forced to demonstrate its full strength over
  a whole game
  which we are all too curious to see.

  Thomas

  On Sat, 12 Mar 2016, Aja Huang wrote:

Thanks all. AlphaGo has won the match against Lee
Sedol. But there are still 2 games to play.
Aja

On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty
<jim.oflaherty...@gmail.com <mailto:jim.oflaherty...@gmail.com> > 
wrote:
  It was exhilerating to witness history being
made! Awesome!

On Sat, Mar 12, 2016 at 2:17 AM, David Fotland
<fotl...@smart-games.com <mailto:fotl...@smart-games.com> > wrote:

  Tremendous games by AlphaGo.  Congratulations!

   

  From: Computer-go
[mailto:computer-go-boun...@computer-go.org 
<mailto:computer-go-boun...@computer-go.org> ] On
Behalf Of Lukas van de Wiel
  Sent: Saturday, March 12, 2016 12:14 AM
  To: computer-go@computer-go.org 
<mailto:computer-go@computer-go.org> 
  Subject: [Computer-go] Congratulations to
AlphaGo

 

Whoa, what a fight! Well fought, and well won!

Lukas


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



___
 

Re: [Computer-go] Congratulations to AlphaGo

[Jim O'Flaherty]

I think you're correct, Thomas. The challenge is going to be getting ANY
professional to be the one who "takes handicap stones" for the first time
in years. The possible "shame" of doing so is what will make it messy.

Once someone does take that step, though, I think it is only a matter of
time before the rating of humans will be made a subordinate rating relative
to the "objective" rating of the AIs, AlphaGo just being the first. And
that has its own psychological challenges as the Go world has many decades
of handling ELOs and rankings for humans. So, I don't think change in this
area is going to be welcomed anytime soon.


On Sat, Mar 12, 2016 at 3:03 PM, Thomas Wolf  wrote:

> Chris,
>
> Prompted from a discussion on the computer go email list
> (and my last email today) :
>
> We currently have no measure at all to judge how safe a winor loss is at
> any
> stage of the game. The measure applied currently of counting territory does
> only apply if both players try to maximize territory but not if at least
> one
> player maximizes the chance of winning. (I know, it was mentioned already).
>
> But really, comments like "Player ... is catching up" are pretty
> meaningless
> and are only valid if one explicitly mentions points or territorry, and
> adds
> that this has nothing to do with winning probabilities.
>
> Even the winning percentages provided by the computer programs themselves
> are
> no real indicator for winninig chances. They are tools to find the best
> move
> and are a statistical measure over several playout sequences based on
> selfplay
> not based on play against that opponent. Equally, winning percentages
> worked
> out by other computer programs are also not adequate (although they are at
> least unbiased) because they do also not use the real opponents to play out
> the sequences.
>
> The only valid strength indicator would be to gradually increase handicap
> stones or komi for the previous loser in a series of games.
>
> Regards,
> Thomas
>
>
> On Sat, 12 Mar 2016, Sorin Gherman wrote:
>
>
>> It is fascinating indeed to try to find how much stronger is AlphaGo
>> compared to top humans.
>>
>> Given the fact that it is hard to find the reason why Lee Sedol lost, and
>> that AlphaGo seems to get mysteriously ahead without a clear reason, tells
>> me that the difference is definitely more than one stone handicap, maybe
>> 2+
>> stones, as crazy as it may sound given Lee Sedol's level.
>>
>> I am pretty sure he will not accept to play with handicap against AlphaGo
>> though. Maybe "younger wolves" like Ke Jie will though and we will find
>> out.
>>
>> On Mar 12, 2016 11:03 AM, "Thomas Wolf"  wrote:
>>   A suggestion for possible future games to be arranged between
>>   AlphaGo and
>>   strong players:
>>
>>   Whoever lost shall be given 1 stone or the equivalent of 1/2
>>   stone handcap in the
>>   next game. Games should continue until each side has won at
>>   least once. This
>>   way AlphaGo will be forced to demonstrate its full strength over
>>   a whole game
>>   which we are all too curious to see.
>>
>>   Thomas
>>
>>   On Sat, 12 Mar 2016, Aja Huang wrote:
>>
>> Thanks all. AlphaGo has won the match against Lee
>> Sedol. But there are still 2 games to play.
>> Aja
>>
>> On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty
>>  wrote:
>>   It was exhilerating to witness history being
>> made! Awesome!
>>
>> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland
>>  wrote:
>>
>>   Tremendous games by AlphaGo.  Congratulations!
>>
>>
>>
>>   From: Computer-go
>> [mailto:computer-go-boun...@computer-go.org] On
>> Behalf Of Lukas van de Wiel
>>   Sent: Saturday, March 12, 2016 12:14 AM
>>   To: computer-go@computer-go.org
>>   Subject: [Computer-go] Congratulations to
>> AlphaGo
>>
>>
>>
>> Whoa, what a fight! Well fought, and well won!
>>
>> Lukas
>>
>>
>> ___
>> 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
> 

Re: [Computer-go] Congratulations to AlphaGo

[Brian Sheppard]

Playing on KGS will give a good sense. Players have sustained ranks between 9 
and 10 dan there, but never over 10 dan. If AlphaGo can sustain over 10 dan, 
then there is clear separation.

-Original Message-
From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Thomas Wolf
Sent: Saturday, March 12, 2016 4:04 PM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] Congratulations to AlphaGo

Chris,

Prompted from a discussion on the computer go email list (and my last email 
today) :

We currently have no measure at all to judge how safe a winor loss is at any 
stage of the game. The measure applied currently of counting territory does 
only apply if both players try to maximize territory but not if at least one 
player maximizes the chance of winning. (I know, it was mentioned already).

But really, comments like "Player ... is catching up" are pretty meaningless 
and are only valid if one explicitly mentions points or territorry, and adds 
that this has nothing to do with winning probabilities.

Even the winning percentages provided by the computer programs themselves are 
no real indicator for winninig chances. They are tools to find the best move 
and are a statistical measure over several playout sequences based on selfplay 
not based on play against that opponent. Equally, winning percentages worked 
out by other computer programs are also not adequate (although they are at 
least unbiased) because they do also not use the real opponents to play out the 
sequences.

The only valid strength indicator would be to gradually increase handicap 
stones or komi for the previous loser in a series of games.

Regards,
Thomas

On Sat, 12 Mar 2016, Sorin Gherman wrote:

> 
> It is fascinating indeed to try to find how much stronger is AlphaGo 
> compared to top humans.
> 
> Given the fact that it is hard to find the reason why Lee Sedol lost, 
> and that AlphaGo seems to get mysteriously ahead without a clear 
> reason, tells me that the difference is definitely more than one stone 
> handicap, maybe 2+ stones, as crazy as it may sound given Lee Sedol's level.
> 
> I am pretty sure he will not accept to play with handicap against 
> AlphaGo though. Maybe "younger wolves" like Ke Jie will though and we will 
> find out.
> 
> On Mar 12, 2016 11:03 AM, "Thomas Wolf" <tw...@brocku.ca> wrote:
>   A suggestion for possible future games to be arranged between
>   AlphaGo and
>   strong players:
>
>   Whoever lost shall be given 1 stone or the equivalent of 1/2
>   stone handcap in the
>   next game. Games should continue until each side has won at
>   least once. This
>   way AlphaGo will be forced to demonstrate its full strength over
>   a whole game
>   which we are all too curious to see.
>
>   Thomas
>
>   On Sat, 12 Mar 2016, Aja Huang wrote:
>
> Thanks all. AlphaGo has won the match against Lee
> Sedol. But there are still 2 games to play.
> Aja
>
> On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty
> <jim.oflaherty...@gmail.com> wrote:
>   It was exhilerating to witness history being
> made! Awesome!
>
> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland
> <fotl...@smart-games.com> wrote:
>
>   Tremendous games by AlphaGo.  Congratulations!
>
>
>
>   From: Computer-go
> [mailto:computer-go-boun...@computer-go.org] On
> Behalf Of Lukas van de Wiel
>   Sent: Saturday, March 12, 2016 12:14 AM
>   To: computer-go@computer-go.org
>   Subject: [Computer-go] Congratulations to
> AlphaGo
>
>  
>
> Whoa, what a fight! Well fought, and well won!
>
> Lukas
> 
>
> ___
> 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] Congratulations to AlphaGo

[Thomas Wolf]

Chris,

Prompted from a discussion on the computer go email list
(and my last email today) :

We currently have no measure at all to judge how safe a winor loss is at any
stage of the game. The measure applied currently of counting territory does
only apply if both players try to maximize territory but not if at least one
player maximizes the chance of winning. (I know, it was mentioned already).

But really, comments like "Player ... is catching up" are pretty meaningless
and are only valid if one explicitly mentions points or territorry, and adds
that this has nothing to do with winning probabilities.

Even the winning percentages provided by the computer programs themselves are
no real indicator for winninig chances. They are tools to find the best move
and are a statistical measure over several playout sequences based on selfplay
not based on play against that opponent. Equally, winning percentages worked
out by other computer programs are also not adequate (although they are at
least unbiased) because they do also not use the real opponents to play out
the sequences.

The only valid strength indicator would be to gradually increase handicap
stones or komi for the previous loser in a series of games.

Regards,
Thomas

On Sat, 12 Mar 2016, Sorin Gherman wrote:



It is fascinating indeed to try to find how much stronger is AlphaGo
compared to top humans.

Given the fact that it is hard to find the reason why Lee Sedol lost, and
that AlphaGo seems to get mysteriously ahead without a clear reason, tells
me that the difference is definitely more than one stone handicap, maybe 2+
stones, as crazy as it may sound given Lee Sedol's level.

I am pretty sure he will not accept to play with handicap against AlphaGo
though. Maybe "younger wolves" like Ke Jie will though and we will find out.

On Mar 12, 2016 11:03 AM, "Thomas Wolf"  wrote:
  A suggestion for possible future games to be arranged between
  AlphaGo and
  strong players:

  Whoever lost shall be given 1 stone or the equivalent of 1/2
  stone handcap in the
  next game. Games should continue until each side has won at
  least once. This
  way AlphaGo will be forced to demonstrate its full strength over
  a whole game
  which we are all too curious to see.

  Thomas

  On Sat, 12 Mar 2016, Aja Huang wrote:

Thanks all. AlphaGo has won the match against Lee
Sedol. But there are still 2 games to play.
Aja

On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty
 wrote:
      It was exhilerating to witness history being
made! Awesome!

On Sat, Mar 12, 2016 at 2:17 AM, David Fotland
 wrote:

      Tremendous games by AlphaGo.  Congratulations!

       

      From: Computer-go
[mailto:computer-go-boun...@computer-go.org] On
Behalf Of Lukas van de Wiel
      Sent: Saturday, March 12, 2016 12:14 AM
      To: computer-go@computer-go.org
      Subject: [Computer-go] Congratulations to
AlphaGo

 

Whoa, what a fight! Well fought, and well won!

Lukas


___
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] Congratulations to AlphaGo

[Sorin Gherman]

It is fascinating indeed to try to find how much stronger is AlphaGo
compared to top humans.

Given the fact that it is hard to find the reason why Lee Sedol lost, and
that AlphaGo seems to get mysteriously ahead without a clear reason, tells
me that the difference is definitely more than one stone handicap, maybe 2+
stones, as crazy as it may sound given Lee Sedol's level.

I am pretty sure he will not accept to play with handicap against AlphaGo
though. Maybe "younger wolves" like Ke Jie will though and we will find out.
On Mar 12, 2016 11:03 AM, "Thomas Wolf"  wrote:

> A suggestion for possible future games to be arranged between AlphaGo and
> strong players:
>
> Whoever lost shall be given 1 stone or the equivalent of 1/2 stone handcap
> in the
> next game. Games should continue until each side has won at least once.
> This
> way AlphaGo will be forced to demonstrate its full strength over a whole
> game
> which we are all too curious to see.
>
> Thomas
>
> On Sat, 12 Mar 2016, Aja Huang wrote:
>
> Thanks all. AlphaGo has won the match against Lee Sedol. But there are
>> still 2 games to play.
>> Aja
>>
>> On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty <
>> jim.oflaherty...@gmail.com> wrote:
>>   It was exhilerating to witness history being made! Awesome!
>>
>> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland 
>> wrote:
>>
>>   Tremendous games by AlphaGo.  Congratulations!
>>
>>
>>
>>   From: Computer-go [mailto:computer-go-boun...@computer-go.org] On
>> Behalf Of Lukas van de Wiel
>>   Sent: Saturday, March 12, 2016 12:14 AM
>>   To: computer-go@computer-go.org
>>   Subject: [Computer-go] Congratulations to AlphaGo
>>
>>
>>
>> Whoa, what a fight! Well fought, and well won!
>>
>> Lukas
>>
>>
>> ___
>> 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] Congratulations to AlphaGo

[Thomas Wolf]

Hi Ingo,

I have the manuscript of 2 books with each 100 computer generated problems
which 1st class insei Yutae Seo (Korea) picked out of 20,000 computer
generated problems, working for 5 months on this selection. Many have a tricky
ko status. I am happy to provide them.

Simpler even and more revealing would be to write down semeai problems using,
for example, the work of Teigo Nakamura. These problems can be evaluated in no
time once one understood the math but which take arbitrarily long to solve if
a brute force search would be applied. Simple pattern matching should not help
there.

Finally, there are seki problems which I showed several professional players,
including famous 9p who could not tell whether the game was over or not.

Lot's of fun tests one could do.

Cheers, Thomas.

On Sat, 12 Mar 2016, "Ingo Althöfer" wrote:


Hi Thomas,

Von: "Thomas Wolf" 

A suggestion for possible future games to be arranged between AlphaGo and
strong players:

Whoever lost shall be given 1 stone or the equivalent of 1/2 stone handcap in 
the
next game. Games should continue until each side has won at least once. This
way AlphaGo will be forced to demonstrate its full strength over a whole game
which we are all too curious to see.


That is one interesting proposal. I have another one:
You are the master of computer tsume go.
Give DeepMind a set of your tsume go compositions (from easy
to really difficult) and let them test which of the problems
AlphaGo can solve.

Cheers, 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] Congratulations to AlphaGo

[Michael Alford]

Give it the hatsuyo-ron :)

On Mar 12, 2016, at 11:12 AM, Ingo Althöfer wrote:

> Hi Thomas,
> 
> Von: "Thomas Wolf" 
>> A suggestion for possible future games to be arranged between AlphaGo and
>> strong players:
>> 
>> Whoever lost shall be given 1 stone or the equivalent of 1/2 stone handcap 
>> in the
>> next game. Games should continue until each side has won at least once. This
>> way AlphaGo will be forced to demonstrate its full strength over a whole game
>> which we are all too curious to see.
> 
> That is one interesting proposal. I have another one:
> You are the master of computer tsume go.
> Give DeepMind a set of your tsume go compositions (from easy
> to really difficult) and let them test which of the problems
> AlphaGo can solve.
> 
> Cheers, 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] Congratulations to AlphaGo

[Ingo Althöfer]

Hi Thomas,

Von: "Thomas Wolf" 
> A suggestion for possible future games to be arranged between AlphaGo and
> strong players:
> 
> Whoever lost shall be given 1 stone or the equivalent of 1/2 stone handcap in 
> the
> next game. Games should continue until each side has won at least once. This
> way AlphaGo will be forced to demonstrate its full strength over a whole game
> which we are all too curious to see.

That is one interesting proposal. I have another one:
You are the master of computer tsume go.
Give DeepMind a set of your tsume go compositions (from easy
to really difficult) and let them test which of the problems
AlphaGo can solve.

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

Re: [Computer-go] Congratulations to AlphaGo

[Jim O'Flaherty]

I LOVE this suggestion!


On Sat, Mar 12, 2016 at 1:02 PM, Thomas Wolf  wrote:

> A suggestion for possible future games to be arranged between AlphaGo and
> strong players:
>
> Whoever lost shall be given 1 stone or the equivalent of 1/2 stone handcap
> in the
> next game. Games should continue until each side has won at least once.
> This
> way AlphaGo will be forced to demonstrate its full strength over a whole
> game
> which we are all too curious to see.
>
> Thomas
>
>
> On Sat, 12 Mar 2016, Aja Huang wrote:
>
> Thanks all. AlphaGo has won the match against Lee Sedol. But there are
>> still 2 games to play.
>> Aja
>>
>> On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty <
>> jim.oflaherty...@gmail.com> wrote:
>>   It was exhilerating to witness history being made! Awesome!
>>
>> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland 
>> wrote:
>>
>>   Tremendous games by AlphaGo.  Congratulations!
>>
>>
>>
>>   From: Computer-go [mailto:computer-go-boun...@computer-go.org] On
>> Behalf Of Lukas van de Wiel
>>   Sent: Saturday, March 12, 2016 12:14 AM
>>   To: computer-go@computer-go.org
>>   Subject: [Computer-go] Congratulations to AlphaGo
>>
>>
>>
>> Whoa, what a fight! Well fought, and well won!
>>
>> Lukas
>>
>>
>> ___
>> 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] Congratulations to AlphaGo

[Thomas Wolf]

A suggestion for possible future games to be arranged between AlphaGo and
strong players:

Whoever lost shall be given 1 stone or the equivalent of 1/2 stone handcap in 
the
next game. Games should continue until each side has won at least once. This
way AlphaGo will be forced to demonstrate its full strength over a whole game
which we are all too curious to see.

Thomas

On Sat, 12 Mar 2016, Aja Huang wrote:


Thanks all. AlphaGo has won the match against Lee Sedol. But there are still 2 
games to play.
Aja

On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty  
wrote:
  It was exhilerating to witness history being made! Awesome!

On Sat, Mar 12, 2016 at 2:17 AM, David Fotland  wrote:

  Tremendous games by AlphaGo.  Congratulations!

   

  From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf 
Of Lukas van de Wiel
  Sent: Saturday, March 12, 2016 12:14 AM
  To: computer-go@computer-go.org
  Subject: [Computer-go] Congratulations to AlphaGo

 

Whoa, what a fight! Well fought, and well won!

Lukas


___
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] Congratulations to AlphaGo

[Hideki Kato]

Congratulations again, Aja!

Once you told me (or I told you?) that "Go is fighting!".  Now 
which do you think, fighting or (whole-board) perspective?

Best regrads, Hideki

Aja Huang: 
: 
>Thanks all. AlphaGo has won the match against Lee Sedol. But there are
>still 2 games to play.
>
>Aja
>
>On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty 
>wrote:
>
>> It was exhilerating to witness history being made! Awesome!
>>
>> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland 
>> wrote:
>>
>>> Tremendous games by AlphaGo.  Congratulations!
>>>
>>>
>>>
>>> *From:* Computer-go [mailto:computer-go-boun...@computer-go.org] *On
>>> Behalf Of *Lukas van de Wiel
>>> *Sent:* Saturday, March 12, 2016 12:14 AM
>>> *To:* computer-go@computer-go.org
>>> *Subject:* [Computer-go] Congratulations to AlphaGo
>>>
>>>
>>>
>>> Whoa, what a fight! Well fought, and well won!
>>>
>>> Lukas
>>>
>>> ___
>>> Computer-go mailing list
>>> Computer-go@computer-go.org
>>> http://computer-go.org/mailman/listinfo/computer-go
>>>
>>
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
> inline file
>___
>Computer-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

Re: [Computer-go] Congratulations to AlphaGo

[Ingo Althöfer]

Dear Aja,

congratulations to you and the whole AlphaGo team for this
awesome performance of your bot!

I fully understand that you take also the last two games seriously.
But, please, do it in such a way that Lee Sedol will be willing
to support you in further matches to come. 

Enjoy the day,
Ingo.

PS. Someone else mentioned it already: Your dress code was really
impressive. Maybe you can come to the Computer Games conference
in Leiden (June 30 - July 1) in exactly this jacket. (We will
organize a Union Jack for you :-).

PS-2. I spoke with an outsider. He thought that "Alpha"Go was
meant in the spirit of pre"Beta"version and asked: how strong will
the beta be and how strong the true engine?
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo

[Olivier Teytaud]

And please tell us how many stones AlphaGo can give to Aja or
to other strong players :-)

(well, I understand you have the two last games to take care of :-) )

On Sat, Mar 12, 2016 at 12:07 PM, Erik van der Werf <
erikvanderw...@gmail.com> wrote:

> Congratulations Aja & Deepmind team!
>
> Now that the victory is clear, perhaps you can say a bit more on the
> latest developments? Any major scientific breakthroughs beyond what we
> already know from the Nature paper?
>
> Enjoy the moments!
>
> Erik
>
>
> On Sat, Mar 12, 2016 at 9:53 AM, Aja Huang  wrote:
>
>> Thanks all. AlphaGo has won the match against Lee Sedol. But there are
>> still 2 games to play.
>>
>> Aja
>>
>> On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty <
>> jim.oflaherty...@gmail.com> wrote:
>>
>>> It was exhilerating to witness history being made! Awesome!
>>>
>>> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland 
>>> wrote:
>>>
 Tremendous games by AlphaGo.  Congratulations!



 *From:* Computer-go [mailto:computer-go-boun...@computer-go.org] *On
 Behalf Of *Lukas van de Wiel
 *Sent:* Saturday, March 12, 2016 12:14 AM
 *To:* computer-go@computer-go.org
 *Subject:* [Computer-go] Congratulations to AlphaGo



 Whoa, what a fight! Well fought, and well won!

 Lukas

 ___
 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
>



-- 
=
Olivier Teytaud, olivier.teyt...@inria.fr, TAO, LRI, UMR 8623(CNRS - Univ.
Paris-Sud),
bat 490 Univ. Paris-Sud F-91405 Orsay Cedex France
http://www.slideshare.net/teytaud
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Congratulations to AlphaGo

[Erik van der Werf]

Congratulations Aja & Deepmind team!

Now that the victory is clear, perhaps you can say a bit more on the latest
developments? Any major scientific breakthroughs beyond what we already
know from the Nature paper?

Enjoy the moments!

Erik


On Sat, Mar 12, 2016 at 9:53 AM, Aja Huang  wrote:

> Thanks all. AlphaGo has won the match against Lee Sedol. But there are
> still 2 games to play.
>
> Aja
>
> On Sat, Mar 12, 2016 at 5:49 PM, Jim O'Flaherty <
> jim.oflaherty...@gmail.com> wrote:
>
>> It was exhilerating to witness history being made! Awesome!
>>
>> On Sat, Mar 12, 2016 at 2:17 AM, David Fotland 
>> wrote:
>>
>>> Tremendous games by AlphaGo.  Congratulations!
>>>
>>>
>>>
>>> *From:* Computer-go [mailto:computer-go-boun...@computer-go.org] *On
>>> Behalf Of *Lukas van de Wiel
>>> *Sent:* Saturday, March 12, 2016 12:14 AM
>>> *To:* computer-go@computer-go.org
>>> *Subject:* [Computer-go] Congratulations to AlphaGo
>>>
>>>
>>>
>>> Whoa, what a fight! Well fought, and well won!
>>>
>>> Lukas
>>>
>>> ___
>>> 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] Congratulations to AlphaGo

[Darren Cook]

Well done, Aja and all the DeepMind team (including all the "backroom
boys" who've given the reliability on the hardware side).

BTW, I've gained great pleasure seeing you sitting there with the union
jack, representing queen and country; you'll probably receive a
knighthood. :-)

> Thanks all. AlphaGo has won the match against Lee Sedol. But there
> are still 2 games to play.

I love your focus! The mainstream media might start to lose interest
now, but at least the people on this list appreciate the implications of
the difference between 5-0 and 3-2. Best of luck in the last two games!

(And just when you thought you were almost back to a nice quiet studious
life, I heard rumour (*) that a Ke Jie match is coming soon.)

Darren

*: I say rumour, as the source was an interview with Demis Hassabis, but
only published in Chinese.

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

Re: [Computer-go] Congratulations to AlphaGo

[Hideki Kato]

Congratulations to DeepMind team!  What an excellent full-board 
perspective.

Hideki

Lukas van de Wiel: 

Re: [Computer-go] Congratulations to AlphaGo

[Jim O'Flaherty]

It was exhilerating to witness history being made! Awesome!

On Sat, Mar 12, 2016 at 2:17 AM, David Fotland 
wrote:

> Tremendous games by AlphaGo.  Congratulations!
>
>
>
> *From:* Computer-go [mailto:computer-go-boun...@computer-go.org] *On
> Behalf Of *Lukas van de Wiel
> *Sent:* Saturday, March 12, 2016 12:14 AM
> *To:* computer-go@computer-go.org
> *Subject:* [Computer-go] Congratulations to AlphaGo
>
>
>
> Whoa, what a fight! Well fought, and well won!
>
> Lukas
>
> ___
> 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] Congratulations to AlphaGo

[David Fotland]

Tremendous games by AlphaGo.  Congratulations!

 

From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Lukas van de Wiel
Sent: Saturday, March 12, 2016 12:14 AM
To: computer-go@computer-go.org
Subject: [Computer-go] Congratulations to AlphaGo

 

Whoa, what a fight! Well fought, and well won!

Lukas

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