Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

[Brian Sheppard]

I remember another way to estimate peak capabilities. This one was used in the 
late 1970's by Ken Thompson / Belle, but maybe was invented earlier: play 
handicap matches at different time controls, and fit a quadratic curve to the 
data. If your program is strong enough, then additional computational effort 
shows diminishing returns. If your program is too weak, then the performance 
scales linearly, and you don't see diminishing returns to higher computational 
effort.

It is also possible to have a peak that falls short of perfection if your 
program's algorithms are not asymptotically optimal, but that was not a problem 
for chess programs. Belle was 1100 rating points lower than current programs, 
and it already showed diminishing returns. I recall that the method gave 
reasonable results. E.g., I remember estimating that Belle would need at least 
depth 13 searches to contend for championship caliber.

-Original Message-
From: Brian Sheppard [mailto:sheppar...@aol.com] 
Sent: Tuesday, March 15, 2016 6:20 PM
To: 'computer-go@computer-go.org' 
Subject: RE: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

>So a small error in the opening or middle game can literally be worth anything 
>by the time the game ends.

These are my estimates: human pros >= 24 points lost, and >= 5 game-losing 
errors against other human pros.

I relayed my experience of a comparable experiment with chess, and how those 
estimates proved to be loose lower bounds, and it would not surprise me if 
these estimates are also far from perfection.

I urge you to construct a model that you feel embodies important 
characteristics, and get back to us with your estimates.

-Original Message-
From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Darren Cook
Sent: Monday, March 14, 2016 5:15 PM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

> You can also look at the score differentials. If the game is perfect, 
> then the game ends up on 7 points every time. If players made one 
> small error (2 points), then the distribution would be much narrower 
> than it is.

I was with you up to this point, but players (computer and strong
humans) play to win, not to maximize the score. So a small error in the opening 
or middle game can literally be worth anything by the time the game ends.

> I am certain that there is a vast gap between humans and perfect play. 
> Maybe 24 points? Four stones??

24pts would be about two stones (if each handicap stone is twice komi, e.g. see 
http://senseis.xmp.net/?topic=2464).

The old saying is that a pro would need to take 3 to 4 stones against god (i.e. 
perfect play).

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] AlphaGo & DCNN: Handling long-range dependency

[Brian Sheppard]

>So a small error in the opening or middle game can literally be worth anything 
>by the time the game ends.

These are my estimates: human pros >= 24 points lost, and >= 5 game-losing 
errors against other human pros.

I relayed my experience of a comparable experiment with chess, and how those 
estimates proved to be loose lower bounds, and it would not surprise me if 
these estimates are also far from perfection.

I urge you to construct a model that you feel embodies important 
characteristics, and get back to us with your estimates.

-Original Message-
From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of 
Darren Cook
Sent: Monday, March 14, 2016 5:15 PM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

> You can also look at the score differentials. If the game is perfect, 
> then the game ends up on 7 points every time. If players made one 
> small error (2 points), then the distribution would be much narrower 
> than it is.

I was with you up to this point, but players (computer and strong
humans) play to win, not to maximize the score. So a small error in the opening 
or middle game can literally be worth anything by the time the game ends.

> I am certain that there is a vast gap between humans and perfect play. 
> Maybe 24 points? Four stones??

24pts would be about two stones (if each handicap stone is twice komi, e.g. see 
http://senseis.xmp.net/?topic=2464).

The old saying is that a pro would need to take 3 to 4 stones against god (i.e. 
perfect play).

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] Final score 4-1 - congratulations to AlphaGo team!

[Freeman Ng]

>
> On 15.03.2016 13:10, Petr Baudis wrote:
>
>>AlphaGo has won the final game, tenaciously catching up after a tesuji
>> mistake in the beginning
>>
>
> No. Do not trust Redmond's positional judgement. IMO, after the initial
> tesuji sequence, the position was balanced. (Kim said: White was a little
> better at that moment.)


For what it's worth, Hassabis called it a tesuji mistake
 from which
AlphaGo had to "claw back". Of course, this was in real time and may or may
not have reflected AlphaGo's actual analysis.

Freeman


*_*
*|| Freeman Ng - www.AuthorFreeman.com *
*||**Who Am I? - a personalizable picture book*
*||**Haiku Diem - a daily haiku feed *
*||**Joan - a novel of Joan of Arc*
***
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Final score 4-1 - congratulations to AlphaGo team!

[Robert Jasiek]

Congratulations!

On 15.03.2016 13:10, Petr Baudis wrote:

   AlphaGo has won the final game, tenaciously catching up after a tesuji
mistake in the beginning


No. Do not trust Redmond's positional judgement. IMO, after the initial 
tesuji sequence, the position was balanced. (Kim said: White was a 
little better at that moment.)


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

Re: [Computer-go] Final score 4-1 - congratulations to AlphaGo team!

[valkyria]

I would also like to congratulate the Alpha-Go team for this fantastic
result now when the dust have settled!

I think after all games have been played me feeling is that Alpha-go is
a little stronger then 9 Dan pro level, but of course still far away 
from

perfect play.

My suspicion of the main weakness is that the neural networks sometimes
completely overlook surprising moves that touches many areas with 
overlapping

aji. In these cases local shapes does not really mean much.

Everyone was wondering if Alphago could handle many complex local 
situations
simultaneously. My feeling is that this is not a problem because the 
mover ordering

straight forward local fights is so good for Alphago.

So what might be remaining weaknesses is that bad aji overlap from many 
areas move
ordering might be difficult if the neural networks cannot handle the aji 
by
generalizing from learning games. There are holes in move ordering and 
this become

a problem when local branching factor get very high.

At some point global search with the massive amount of hardware will see 
the problems,
but if the value network for example leads Alphago to build a mojo with 
holes in it
without correctly understanding the tactical consequences it might often 
get in into trouble.
But the opponent needs to play perfectly when the opportunity comes, so 
I think pros
in the future would have difficulties provoke these kinds of mistakes. 
In fact I think they

have to play patiently and let Alphago trap itself.

This is also my experience from playing Correspondence go with Valkyria 
on 9x9.
The program is very far from perfect play, but with long thinking times 
one
must play patient but sharp. Setting traps does not work, but if one is 
luckily the program
will go into some position which it overvalues spontaneously and when 
the opportunity to win

comes.

Alphago is a little bit similar, but of course on 19x19 using 2 minutes 
per move which is
close to unbelievable if it were not for advances in deep learning 
networks.


Best
Magnus Persson



On 2016-03-15 13:10, Petr Baudis wrote:

AlphaGo has won the final game, tenaciously catching up after a tesuji
mistake in the beginning - a great data point that it can also deal 
with

somewhat disadvantageous position well.  It has received honorary 9p
from the KBA.

  I can only quote David Silver: "Wow, what an amazing week this has
been."  This is a huge leap for AI in general, maybe the most 
convincing

application demonstration of deep learning up to now.

  (The take-away for me personally, even if obvious in retrospect, 
would

be not to focus on one field too much.  I got similar ideas not long
after I actually stopped doing Computer Go and took a wide look at 
other
Machine Learning areas - well, three weeks later the Clark 
paper

came out. :) I came to believe that transferring ideas and models from
one field to another has one of the best effort / value tradeoffs, not
just personally but also for the scientific progress as a whole.)

  I do hope that Aja will have time and be willing to answer some of 
our

technical questions now after taking a while to recover from what must
have been an exhausting week.

  But now, onto getting pro Go players on our PCs, and applying this on
new things! :)

Petr Baudis
___
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] Final score 4-1 - congratulations to AlphaGo team!

[Petr Baudis]

  AlphaGo has won the final game, tenaciously catching up after a tesuji
mistake in the beginning - a great data point that it can also deal with
somewhat disadvantageous position well.  It has received honorary 9p
from the KBA.

  I can only quote David Silver: "Wow, what an amazing week this has
been."  This is a huge leap for AI in general, maybe the most convincing
application demonstration of deep learning up to now.

  (The take-away for me personally, even if obvious in retrospect, would
be not to focus on one field too much.  I got similar ideas not long
after I actually stopped doing Computer Go and took a wide look at other
Machine Learning areas - well, three weeks later the Clark paper
came out. :) I came to believe that transferring ideas and models from
one field to another has one of the best effort / value tradeoffs, not
just personally but also for the scientific progress as a whole.)

  I do hope that Aja will have time and be willing to answer some of our
technical questions now after taking a while to recover from what must
have been an exhausting week.

  But now, onto getting pro Go players on our PCs, and applying this on
new things! :)

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