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

Reply via email to