Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-03-13 Thread Stefan Kaitschick 
The evaluation is always at least as deep as leaves of the tree.
Still, you're right that the earlier in the game, the bigger the inherent
uncertainty.
One thing I don't understand: if the network does a thumbs up or down,
instead of answering with a probability,
what is the use of MSE? Why not just prediction rate?

On Thu, Feb 4, 2016 at 8:34 PM, Álvaro Begué  wrote:

> I am not sure how exactly they define MSE. If you look at the plot in
> figure 2b, the MSE at the very beginning of the game (where you can't
> possibly know anything about the result) is 0.50. That suggests it's
> something else than your [very sensible] interpretation.
>
> Álvaro.
>
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Detlef Schmicker 
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1

> One possibility is that 0=loss, 1=win, and the number they are
quoting is
> sqrt(average((prediction-outcome)^2)).


this makes perfectly sense for figure 2. even playouts seem reasonable.

But figure 2 is not consistent with the numbers in section 3 would be
0.234 (test set of the self-play data base. The figure looks more like
0.3 - 0.35 or even higher...



Am 04.02.2016 um 21:43 schrieb Álvaro Begué:
> I just want to see how to get 0.5 for the initial position on the
> board with some definition.
> 
> One possibility is that 0=loss, 1=win, and the number they are
> quoting is sqrt(average((prediction-outcome)^2)).
> 
> 
> On Thu, Feb 4, 2016 at 3:40 PM, Hideki Kato
>  wrote:
> 
>> I think the error is defined as the difference between the output
>> of the value network and the average output of the simulations
>> done by the policy network (RL) at each position.
>> 
>> Hideki
>> 
>> Michael Markefka:
>>

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Hideki Kato 
Detlef Schmicker: <56b385ce.4080...@physik.de>: 
>-BEGIN PGP SIGNED MESSAGE-
>Hash: SHA1
>
>Hi,
>
>I try to reproduce numbers from section 3: training the value network
>
>On the test set of kgs games the MSE is 0.37. Is it correct, that the
>results are represented as +1 and -1?

Looks correct.

>This means, that in a typical board position you get a value of
>1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70% ?!

Since all positions of all games in the dataset are used, 
winrate should distributes from 0% to 100%, or -1 to 1, not 1.  
Then, the number 70% could be wrong.  MSE is 0.37 just means the 
average error is about 0.6, I think.

Hideki

>Is it really true, that a typical kgs 6d+ position is judeged with
>such a high win rate (even though it it is overfitted, so the test set
>number is to bad!), or do I misinterpret the MSE calculation?!
>
>Any help would be great,
>
>Detlef
>
>Am 27.01.2016 um 19:46 schrieb Aja Huang:
>> Hi all,
>> 
>> We are very excited to announce that our Go program, AlphaGo, has
>> beaten a professional player for the first time. AlphaGo beat the
>> European champion Fan Hui by 5 games to 0. We hope you enjoy our
>> paper, published in Nature today. The paper and all the games can
>> be found here:
>> 
>> http://www.deepmind.com/alpha-go.html
>> 
>> AlphaGo will be competing in a match against Lee Sedol in Seoul,
>> this March, to see whether we finally have a Go program that is
>> stronger than any human!
>> 
>> Aja
>> 
>> PS I am very busy preparing AlphaGo for the match, so apologies in
>> advance if I cannot respond to all questions about AlphaGo.
>> 
>> 
>> 
>> ___ Computer-go mailing
>> list Computer-go@computer-go.org 
>> http://computer-go.org/mailman/listinfo/computer-go
>> 
>-BEGIN PGP SIGNATURE-
>Version: GnuPG v2.0.22 (GNU/Linux)
>
>iQIcBAEBAgAGBQJWs4XOAAoJEInWdHg+Znf4btkQAKP5T6o8qk9Fv1z/JJGTdcph
>A8rXWXNPNybSTqBVh7IJHKB9WxNIIOODjj6JYL4vhjFC+Eqy7AcpHkFZEn+f9j2G
>Kl3w6G88M9P8/iCn++pNHF3dPTrsn2doUcUjF1fJZsKeNCISuvbHwbzgXupna+lH
>qeCpYx/VBQMJIdhGqTmWsQozbFMFbeTumMH94UwNkTwo4Tnue/UCJweU0bWIIt0D
>TtCyLDsDcFy/qNrZC97858tpvOpo3hWs7pLf8ed+9r13UGeJhQJkedg6Oq0e5wTl
>Ye36Z1/2QHnQtvUbk6yjd6GMK0lo6LOOC1lTpp1nFvzcZ4ifrY2LejQ+7nWmafRq
>y46aeH4jqtEF2GXsFTq7ATftSYoeeUzgKxb8t4D8ShP3cRRWkpHFyGtdq25yYO2P
>hp35zJHAlCtUUOzy0YBY+mngYnbwxjp1ykwUi5DmubtRTfhf4pTAH+DF5/UeItn/
>IebMR9JlfCsFJZ7BLq7P7UoHz0eiG2vVKNXUP0Np4LA3KAm1IAOfJWRmLP9TrHOX
>32vdIQLXlbDMTfbloXrFjQo3wm3pKrKstI41Pyoo5d8kE8FPxjCga6EfmarjRKGY
>UBf7Vz8iijGWjTjszui78HlJBIGls9qyuxNUcBN4+kfJJLP633HO+tmDM1hcsD4D
>BPtgsamuDtf5jvxGTa9d
>=Ab0j
>-END PGP SIGNATURE-
>___
>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] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Detlef Schmicker 
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1

>> Since all positions of all games in the dataset are used, winrate
>> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the
>> number 70% could be wrong.  MSE is 0.37 just means the average
>> error is about 0.6, I think.

0.6 in the range of -1 to 1,

which means -1 (eg lost by b) games -> typical value -0.4
and +1 games -> typical value +0.4 of the value network

if I rescale -1 to +1 to  0 - 100% (eg winrate for b) than I get about
30% for games lost by b and 70% for games won by B?

Detlef


Am 04.02.2016 um 20:10 schrieb Hideki Kato:
> Detlef Schmicker: <56b385ce.4080...@physik.de>: Hi,
> 
> I try to reproduce numbers from section 3: training the value
> network
> 
> On the test set of kgs games the MSE is 0.37. Is it correct, that
> the results are represented as +1 and -1?
> 
>> Looks correct.
> 
> This means, that in a typical board position you get a value of 
> 1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70%
> ?!
> 
>> Since all positions of all games in the dataset are used, winrate
>> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the
>> number 70% could be wrong.  MSE is 0.37 just means the average
>> error is about 0.6, I think.
> 
>> Hideki
> 
> Is it really true, that a typical kgs 6d+ position is judeged with 
> such a high win rate (even though it it is overfitted, so the test
> set number is to bad!), or do I misinterpret the MSE calculation?!
> 
> Any help would be great,
> 
> Detlef
> 
> Am 27.01.2016 um 19:46 schrieb Aja Huang:
 Hi all,
 
 We are very excited to announce that our Go program, AlphaGo,
 has beaten a professional player for the first time. AlphaGo
 beat the European champion Fan Hui by 5 games to 0. We hope
 you enjoy our paper, published in Nature today. The paper and
 all the games can be found here:
 
 http://www.deepmind.com/alpha-go.html
 
 AlphaGo will be competing in a match against Lee Sedol in
 Seoul, this March, to see whether we finally have a Go
 program that is stronger than any human!
 
 Aja
 
 PS I am very busy preparing AlphaGo for the match, so
 apologies in advance if I cannot respond to all questions
 about AlphaGo.
 
 
 
 ___ 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
-BEGIN PGP SIGNATURE-
Version: GnuPG v2.0.22 (GNU/Linux)
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=TnKW
-END PGP SIGNATURE-
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Álvaro Begué 
I am not sure how exactly they define MSE. If you look at the plot in
figure 2b, the MSE at the very beginning of the game (where you can't
possibly know anything about the result) is 0.50. That suggests it's
something else than your [very sensible] interpretation.

Álvaro.



On Thu, Feb 4, 2016 at 2:24 PM, Detlef Schmicker  wrote:

> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> >> Since all positions of all games in the dataset are used, winrate
> >> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the
> >> number 70% could be wrong.  MSE is 0.37 just means the average
> >> error is about 0.6, I think.
>
> 0.6 in the range of -1 to 1,
>
> which means -1 (eg lost by b) games -> typical value -0.4
> and +1 games -> typical value +0.4 of the value network
>
> if I rescale -1 to +1 to  0 - 100% (eg winrate for b) than I get about
> 30% for games lost by b and 70% for games won by B?
>
> Detlef
>
>
> Am 04.02.2016 um 20:10 schrieb Hideki Kato:
> > Detlef Schmicker: <56b385ce.4080...@physik.de>: Hi,
> >
> > I try to reproduce numbers from section 3: training the value
> > network
> >
> > On the test set of kgs games the MSE is 0.37. Is it correct, that
> > the results are represented as +1 and -1?
> >
> >> Looks correct.
> >
> > This means, that in a typical board position you get a value of
> > 1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70%
> > ?!
> >
> >> Since all positions of all games in the dataset are used, winrate
> >> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the
> >> number 70% could be wrong.  MSE is 0.37 just means the average
> >> error is about 0.6, I think.
> >
> >> Hideki
> >
> > Is it really true, that a typical kgs 6d+ position is judeged with
> > such a high win rate (even though it it is overfitted, so the test
> > set number is to bad!), or do I misinterpret the MSE calculation?!
> >
> > Any help would be great,
> >
> > Detlef
> >
> > Am 27.01.2016 um 19:46 schrieb Aja Huang:
>  Hi all,
> 
>  We are very excited to announce that our Go program, AlphaGo,
>  has beaten a professional player for the first time. AlphaGo
>  beat the European champion Fan Hui by 5 games to 0. We hope
>  you enjoy our paper, published in Nature today. The paper and
>  all the games can be found here:
> 
>  http://www.deepmind.com/alpha-go.html
> 
>  AlphaGo will be competing in a match against Lee Sedol in
>  Seoul, this March, to see whether we finally have a Go
>  program that is stronger than any human!
> 
>  Aja
> 
>  PS I am very busy preparing AlphaGo for the match, so
>  apologies in advance if I cannot respond to all questions
>  about AlphaGo.
> 
> 
> 
>  ___ 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
> -BEGIN PGP SIGNATURE-
> Version: GnuPG v2.0.22 (GNU/Linux)
>
> iQIcBAEBAgAGBQJWs6WFAAoJEInWdHg+Znf4eTsP/21vawWsmrZkDuAjTkwbKB2S
> 7LpLi3huuLlepkulmUr3rIUvDHhTOwD04pDHjjVrIDBB1k3JjQQ/YKWDfijQQYu6
> ZI1GK55pglUPH+uc+rxfM89ziJwCQrza71l5XU+5ffcBwxRjeAL+D1fGGyr0CPlv
> WKR/Q07XDslXhwlk2O6NDpd80d38dMlMV9lO4s8Zf3Y+o8WJOuyEdybRpg8VOibq
> o59RCAWUiVkTs++iSihcIrVAwGnLtkPyMJ/lBN6zMyZQeuM0dyYL+IAoMH9IdCLQ
> 0jpbtJEqtSsp1ZjWs9s/M4pxKlvUZLThtYSjyGDJ2qDYXII6DeBgxHGUoUxc5A6a
> HVF04gG77U2fMCa/6eGlQN2380kNCjdyRCDUZc9St3tbQPnWU+syk6U/inF7bhAA
> 7ONJD0dcjZROmblqurv32pO6sLuS8wA4DfJhpM5xSSJcYI46YQtVWL4OXY+dtx6S
> 6uQ1fiPqgo4WM0iHEOnh7BEz0NqZeahIUJJVmgKODzp2krOqbpOpbwe7WUI7UHmK
> 3LCNC9oMRybNuc+jrbHqFwT+tgQLTqpbHZuDVzKkBcxqPSj7hRvjLXAjkWNCzL7j
> Yo4MySS6rzenuj9ZRSrQDSYfowRZyzPzMnmjkMbM7R7wpR5CL4U95LqOdMnce2IG
> s/6iYcuUH8KqpG9NMy0U
> =TnKW
> -END PGP SIGNATURE-
> ___
> 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] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Álvaro Begué 
The positions they used are not from high-quality games. They actually
include one last move that is completely random.

Álvaro.


On Thursday, February 4, 2016, Detlef Schmicker  wrote:

> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Hi,
>
> I try to reproduce numbers from section 3: training the value network
>
> On the test set of kgs games the MSE is 0.37. Is it correct, that the
> results are represented as +1 and -1?
>
> This means, that in a typical board position you get a value of
> 1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70% ?!
>
> Is it really true, that a typical kgs 6d+ position is judeged with
> such a high win rate (even though it it is overfitted, so the test set
> number is to bad!), or do I misinterpret the MSE calculation?!
>
> Any help would be great,
>
> Detlef
>
> Am 27.01.2016 um 19:46 schrieb Aja Huang:
> > Hi all,
> >
> > We are very excited to announce that our Go program, AlphaGo, has
> > beaten a professional player for the first time. AlphaGo beat the
> > European champion Fan Hui by 5 games to 0. We hope you enjoy our
> > paper, published in Nature today. The paper and all the games can
> > be found here:
> >
> > http://www.deepmind.com/alpha-go.html
> >
> > AlphaGo will be competing in a match against Lee Sedol in Seoul,
> > this March, to see whether we finally have a Go program that is
> > stronger than any human!
> >
> > Aja
> >
> > PS I am very busy preparing AlphaGo for the match, so apologies in
> > advance if I cannot respond to all questions about AlphaGo.
> >
> >
> >
> > ___ Computer-go mailing
> > list Computer-go@computer-go.org 
> > http://computer-go.org/mailman/listinfo/computer-go
> >
> -BEGIN PGP SIGNATURE-
> Version: GnuPG v2.0.22 (GNU/Linux)
>
> iQIcBAEBAgAGBQJWs4XOAAoJEInWdHg+Znf4btkQAKP5T6o8qk9Fv1z/JJGTdcph
> A8rXWXNPNybSTqBVh7IJHKB9WxNIIOODjj6JYL4vhjFC+Eqy7AcpHkFZEn+f9j2G
> Kl3w6G88M9P8/iCn++pNHF3dPTrsn2doUcUjF1fJZsKeNCISuvbHwbzgXupna+lH
> qeCpYx/VBQMJIdhGqTmWsQozbFMFbeTumMH94UwNkTwo4Tnue/UCJweU0bWIIt0D
> TtCyLDsDcFy/qNrZC97858tpvOpo3hWs7pLf8ed+9r13UGeJhQJkedg6Oq0e5wTl
> Ye36Z1/2QHnQtvUbk6yjd6GMK0lo6LOOC1lTpp1nFvzcZ4ifrY2LejQ+7nWmafRq
> y46aeH4jqtEF2GXsFTq7ATftSYoeeUzgKxb8t4D8ShP3cRRWkpHFyGtdq25yYO2P
> hp35zJHAlCtUUOzy0YBY+mngYnbwxjp1ykwUi5DmubtRTfhf4pTAH+DF5/UeItn/
> IebMR9JlfCsFJZ7BLq7P7UoHz0eiG2vVKNXUP0Np4LA3KAm1IAOfJWRmLP9TrHOX
> 32vdIQLXlbDMTfbloXrFjQo3wm3pKrKstI41Pyoo5d8kE8FPxjCga6EfmarjRKGY
> UBf7Vz8iijGWjTjszui78HlJBIGls9qyuxNUcBN4+kfJJLP633HO+tmDM1hcsD4D
> BPtgsamuDtf5jvxGTa9d
> =Ab0j
> -END PGP SIGNATURE-
> ___
> 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] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Detlef Schmicker 
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1

Hi,

I try to reproduce numbers from section 3: training the value network

On the test set of kgs games the MSE is 0.37. Is it correct, that the
results are represented as +1 and -1?

This means, that in a typical board position you get a value of
1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70% ?!

Is it really true, that a typical kgs 6d+ position is judeged with
such a high win rate (even though it it is overfitted, so the test set
number is to bad!), or do I misinterpret the MSE calculation?!

Any help would be great,

Detlef

Am 27.01.2016 um 19:46 schrieb Aja Huang:
> Hi all,
> 
> We are very excited to announce that our Go program, AlphaGo, has
> beaten a professional player for the first time. AlphaGo beat the
> European champion Fan Hui by 5 games to 0. We hope you enjoy our
> paper, published in Nature today. The paper and all the games can
> be found here:
> 
> http://www.deepmind.com/alpha-go.html
> 
> AlphaGo will be competing in a match against Lee Sedol in Seoul,
> this March, to see whether we finally have a Go program that is
> stronger than any human!
> 
> Aja
> 
> PS I am very busy preparing AlphaGo for the match, so apologies in
> advance if I cannot respond to all questions about AlphaGo.
> 
> 
> 
> ___ Computer-go mailing
> list Computer-go@computer-go.org 
> http://computer-go.org/mailman/listinfo/computer-go
> 
-BEGIN PGP SIGNATURE-
Version: GnuPG v2.0.22 (GNU/Linux)

iQIcBAEBAgAGBQJWs4XOAAoJEInWdHg+Znf4btkQAKP5T6o8qk9Fv1z/JJGTdcph
A8rXWXNPNybSTqBVh7IJHKB9WxNIIOODjj6JYL4vhjFC+Eqy7AcpHkFZEn+f9j2G
Kl3w6G88M9P8/iCn++pNHF3dPTrsn2doUcUjF1fJZsKeNCISuvbHwbzgXupna+lH
qeCpYx/VBQMJIdhGqTmWsQozbFMFbeTumMH94UwNkTwo4Tnue/UCJweU0bWIIt0D
TtCyLDsDcFy/qNrZC97858tpvOpo3hWs7pLf8ed+9r13UGeJhQJkedg6Oq0e5wTl
Ye36Z1/2QHnQtvUbk6yjd6GMK0lo6LOOC1lTpp1nFvzcZ4ifrY2LejQ+7nWmafRq
y46aeH4jqtEF2GXsFTq7ATftSYoeeUzgKxb8t4D8ShP3cRRWkpHFyGtdq25yYO2P
hp35zJHAlCtUUOzy0YBY+mngYnbwxjp1ykwUi5DmubtRTfhf4pTAH+DF5/UeItn/
IebMR9JlfCsFJZ7BLq7P7UoHz0eiG2vVKNXUP0Np4LA3KAm1IAOfJWRmLP9TrHOX
32vdIQLXlbDMTfbloXrFjQo3wm3pKrKstI41Pyoo5d8kE8FPxjCga6EfmarjRKGY
UBf7Vz8iijGWjTjszui78HlJBIGls9qyuxNUcBN4+kfJJLP633HO+tmDM1hcsD4D
BPtgsamuDtf5jvxGTa9d
=Ab0j
-END PGP SIGNATURE-
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Detlef Schmicker 
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1

Thanks for the response, I do not refer to the finaly used data set:
in the referred chapter they state, they have used their kgs dataset
in a first try (which is in another part of the paper referred to
being a 6d+ data set).

Am 04.02.2016 um 18:11 schrieb Álvaro Begué:
> The positions they used are not from high-quality games. They
> actually include one last move that is completely random.
> 
> Álvaro.
> 
> 
> On Thursday, February 4, 2016, Detlef Schmicker 
> wrote:
> 
> Hi,
> 
> I try to reproduce numbers from section 3: training the value
> network
> 
> On the test set of kgs games the MSE is 0.37. Is it correct, that
> the results are represented as +1 and -1?
> 
> This means, that in a typical board position you get a value of 
> 1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70%
> ?!
> 
> Is it really true, that a typical kgs 6d+ position is judeged with 
> such a high win rate (even though it it is overfitted, so the test
> set number is to bad!), or do I misinterpret the MSE calculation?!
> 
> Any help would be great,
> 
> Detlef
> 
> Am 27.01.2016 um 19:46 schrieb Aja Huang:
 Hi all,
 
 We are very excited to announce that our Go program, AlphaGo,
 has beaten a professional player for the first time. AlphaGo
 beat the European champion Fan Hui by 5 games to 0. We hope
 you enjoy our paper, published in Nature today. The paper and
 all the games can be found here:
 
 http://www.deepmind.com/alpha-go.html
 
 AlphaGo will be competing in a match against Lee Sedol in
 Seoul, this March, to see whether we finally have a Go
 program that is stronger than any human!
 
 Aja
 
 PS I am very busy preparing AlphaGo for the match, so
 apologies in advance if I cannot respond to all questions
 about AlphaGo.
 
 
 
 ___ 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
> 
-BEGIN PGP SIGNATURE-
Version: GnuPG v2.0.22 (GNU/Linux)
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=p2U5
-END PGP SIGNATURE-
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Álvaro Begué 
I re-read the relevant section and I agree with you. Sorry for adding noise
to the conversation.

Álvaro.







On Thu, Feb 4, 2016 at 12:21 PM, Detlef Schmicker  wrote:

> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Thanks for the response, I do not refer to the finaly used data set:
> in the referred chapter they state, they have used their kgs dataset
> in a first try (which is in another part of the paper referred to
> being a 6d+ data set).
>
> Am 04.02.2016 um 18:11 schrieb Álvaro Begué:
> > The positions they used are not from high-quality games. They
> > actually include one last move that is completely random.
> >
> > Álvaro.
> >
> >
> > On Thursday, February 4, 2016, Detlef Schmicker 
> > wrote:
> >
> > Hi,
> >
> > I try to reproduce numbers from section 3: training the value
> > network
> >
> > On the test set of kgs games the MSE is 0.37. Is it correct, that
> > the results are represented as +1 and -1?
> >
> > This means, that in a typical board position you get a value of
> > 1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70%
> > ?!
> >
> > Is it really true, that a typical kgs 6d+ position is judeged with
> > such a high win rate (even though it it is overfitted, so the test
> > set number is to bad!), or do I misinterpret the MSE calculation?!
> >
> > Any help would be great,
> >
> > Detlef
> >
> > Am 27.01.2016 um 19:46 schrieb Aja Huang:
>  Hi all,
> 
>  We are very excited to announce that our Go program, AlphaGo,
>  has beaten a professional player for the first time. AlphaGo
>  beat the European champion Fan Hui by 5 games to 0. We hope
>  you enjoy our paper, published in Nature today. The paper and
>  all the games can be found here:
> 
>  http://www.deepmind.com/alpha-go.html
> 
>  AlphaGo will be competing in a match against Lee Sedol in
>  Seoul, this March, to see whether we finally have a Go
>  program that is stronger than any human!
> 
>  Aja
> 
>  PS I am very busy preparing AlphaGo for the match, so
>  apologies in advance if I cannot respond to all questions
>  about AlphaGo.
> 
> 
> 
>  ___ 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
> >
> -BEGIN PGP SIGNATURE-
> Version: GnuPG v2.0.22 (GNU/Linux)
>
> iQIcBAEBAgAGBQJWs4idAAoJEInWdHg+Znf4gyEP/iqAdAkxlsilYGQflCyN3z4V
> xg7esBxj2p8cR2SP3erFQNtThDMN+Qr8FNSYMbMHyJRUaJcsEhsk76Qbro/Bh815
> Xk/79w2LF0rdHwzYkIye3YunifIAwREaIXwCokzuPv0zFrKFgCu7UbIpup7oMXdr
> q3c+FvBwjXX/UtChBZC6kC8U2b1dijMnxPOQC05Hw/LMycKinOzzwByKS3CHdzg6
> eFHAAmrJsaY9iJvCyJQL5ZLdOMBVl50iLez5P8F2t1Bf+Qm03w2nnhAWl/3bjyVy
> hdvcNw6VGSUNeXo2wmF8SJoB1fOUOLAVVenc9jJHkcdcRQxSEBzuH25OfPgNTz55
> JgRqiSM0iOeQ9NmQlC1LRz1BDRYRUx0RsaCvcA1G3m5gKCsbbsVkluppNHUzxAUz
> o3+jazCi+88Gb5EZfdKF7p+g0JoWE2OucwXKyzlmUZMz4Hce+zOfSwv2k/9vrTLW
> z0LfKxDbqQG7cj1jVysvTcQvxSkA54cNLtj/uVNzTvoti+pwyscd5DqJ8jXfcHGG
> HZC3tPsVM7wvqf46EGgmjDI9jjhSTzXXdpDW7gfFTtUvZx8S4iGfmxWLod48deIP
> MiLDehl3rQBuQq5fx+i1ZDB3Gej6vvc9MHAiTo+kUf5TCYBMDAaxRt4OiLnK6N+d
> J02Sn7O1jSG4Fw5ud6iR
> =p2U5
> -END PGP SIGNATURE-
> ___
> 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] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Michael Markefka 
That sounds like it'd be the MSE as classification error of the eventual result.

I'm currently not able to look at the paper, but couldn't you use a
softmax output layer with two nodes and take the probability
distribution as winrate?

On Thu, Feb 4, 2016 at 8:34 PM, Álvaro Begué  wrote:
> I am not sure how exactly they define MSE. If you look at the plot in figure
> 2b, the MSE at the very beginning of the game (where you can't possibly know
> anything about the result) is 0.50. That suggests it's something else than
> your [very sensible] interpretation.
>
> Álvaro.
>
>
>
> On Thu, Feb 4, 2016 at 2:24 PM, Detlef Schmicker  wrote:
>>
>> -BEGIN PGP SIGNED MESSAGE-
>> Hash: SHA1
>>
>> >> Since all positions of all games in the dataset are used, winrate
>> >> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the
>> >> number 70% could be wrong.  MSE is 0.37 just means the average
>> >> error is about 0.6, I think.
>>
>> 0.6 in the range of -1 to 1,
>>
>> which means -1 (eg lost by b) games -> typical value -0.4
>> and +1 games -> typical value +0.4 of the value network
>>
>> if I rescale -1 to +1 to  0 - 100% (eg winrate for b) than I get about
>> 30% for games lost by b and 70% for games won by B?
>>
>> Detlef
>>
>>
>> Am 04.02.2016 um 20:10 schrieb Hideki Kato:
>> > Detlef Schmicker: <56b385ce.4080...@physik.de>: Hi,
>> >
>> > I try to reproduce numbers from section 3: training the value
>> > network
>> >
>> > On the test set of kgs games the MSE is 0.37. Is it correct, that
>> > the results are represented as +1 and -1?
>> >
>> >> Looks correct.
>> >
>> > This means, that in a typical board position you get a value of
>> > 1-sqrt(0.37) = 0.4  --> this would correspond to a win rate of 70%
>> > ?!
>> >
>> >> Since all positions of all games in the dataset are used, winrate
>> >> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the
>> >> number 70% could be wrong.  MSE is 0.37 just means the average
>> >> error is about 0.6, I think.
>> >
>> >> Hideki
>> >
>> > Is it really true, that a typical kgs 6d+ position is judeged with
>> > such a high win rate (even though it it is overfitted, so the test
>> > set number is to bad!), or do I misinterpret the MSE calculation?!
>> >
>> > Any help would be great,
>> >
>> > Detlef
>> >
>> > Am 27.01.2016 um 19:46 schrieb Aja Huang:
>>  Hi all,
>> 
>>  We are very excited to announce that our Go program, AlphaGo,
>>  has beaten a professional player for the first time. AlphaGo
>>  beat the European champion Fan Hui by 5 games to 0. We hope
>>  you enjoy our paper, published in Nature today. The paper and
>>  all the games can be found here:
>> 
>>  http://www.deepmind.com/alpha-go.html
>> 
>>  AlphaGo will be competing in a match against Lee Sedol in
>>  Seoul, this March, to see whether we finally have a Go
>>  program that is stronger than any human!
>> 
>>  Aja
>> 
>>  PS I am very busy preparing AlphaGo for the match, so
>>  apologies in advance if I cannot respond to all questions
>>  about AlphaGo.
>> 
>> 
>> 
>>  ___ 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
>> -BEGIN PGP SIGNATURE-
>> Version: GnuPG v2.0.22 (GNU/Linux)
>>
>> iQIcBAEBAgAGBQJWs6WFAAoJEInWdHg+Znf4eTsP/21vawWsmrZkDuAjTkwbKB2S
>> 7LpLi3huuLlepkulmUr3rIUvDHhTOwD04pDHjjVrIDBB1k3JjQQ/YKWDfijQQYu6
>> ZI1GK55pglUPH+uc+rxfM89ziJwCQrza71l5XU+5ffcBwxRjeAL+D1fGGyr0CPlv
>> WKR/Q07XDslXhwlk2O6NDpd80d38dMlMV9lO4s8Zf3Y+o8WJOuyEdybRpg8VOibq
>> o59RCAWUiVkTs++iSihcIrVAwGnLtkPyMJ/lBN6zMyZQeuM0dyYL+IAoMH9IdCLQ
>> 0jpbtJEqtSsp1ZjWs9s/M4pxKlvUZLThtYSjyGDJ2qDYXII6DeBgxHGUoUxc5A6a
>> HVF04gG77U2fMCa/6eGlQN2380kNCjdyRCDUZc9St3tbQPnWU+syk6U/inF7bhAA
>> 7ONJD0dcjZROmblqurv32pO6sLuS8wA4DfJhpM5xSSJcYI46YQtVWL4OXY+dtx6S
>> 6uQ1fiPqgo4WM0iHEOnh7BEz0NqZeahIUJJVmgKODzp2krOqbpOpbwe7WUI7UHmK
>> 3LCNC9oMRybNuc+jrbHqFwT+tgQLTqpbHZuDVzKkBcxqPSj7hRvjLXAjkWNCzL7j
>> Yo4MySS6rzenuj9ZRSrQDSYfowRZyzPzMnmjkMbM7R7wpR5CL4U95LqOdMnce2IG
>> s/6iYcuUH8KqpG9NMy0U
>> =TnKW
>> -END PGP SIGNATURE-
>> ___
>> 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] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Hideki Kato 
I think the error is defined as the difference between the 
output of the value network and the average output of the 
simulations done by the policy network (RL) at each position.

Hideki

Michael Markefka:

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)

2016-02-04 Thread Álvaro Begué 
I just want to see how to get 0.5 for the initial position on the board
with some definition.

One possibility is that 0=loss, 1=win, and the number they are quoting is
sqrt(average((prediction-outcome)^2)).


On Thu, Feb 4, 2016 at 3:40 PM, Hideki Kato  wrote:

> I think the error is defined as the difference between the
> output of the value network and the average output of the
> simulations done by the policy network (RL) at each position.
>
> Hideki
>
> Michael Markefka: