[Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search (value network)
hideki_katoh at ybb.ne.jp
Thu Feb 4 11:10:11 PST 2016
Detlef Schmicker: <56B385CE.4080804 at physik.de>:
>-----BEGIN PGP SIGNED MESSAGE-----
>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% ?!
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.
>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,
>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:
>> 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!
>> 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 at computer-go.org
>-----BEGIN PGP SIGNATURE-----
>Version: GnuPG v2.0.22 (GNU/Linux)
>-----END PGP SIGNATURE-----
>Computer-go mailing list
>Computer-go at computer-go.org
Hideki Kato <mailto:hideki_katoh at ybb.ne.jp>
More information about the Computer-go