[Computer-go] AlphaGo Zero
hideki_katoh at ybb.ne.jp
Sat Oct 21 17:29:17 PDT 2017
The games look like previously published ones. Just
mic: <31fa8de6-c157-5de6-78fb-a66e6957a357 at gmx.de>:
>There are several AlphaGo instances playing against each other on Tygem
>at this moment.
>On 21.10.2017 14:21, David Ongaro wrote:
>> Am 10/21/2017 um 03:12 AM schrieb uurtamo .:
>>> This sounds like a nice idea that is a misguided project.
>>> Just accept that something awesome happened and that studying those
>>> things that make it work well are more interesting than translating
>>> coefficients into a bad understanding for people.
>>> I'm sorry that this NN can't teach anyone how to be a better player
>>> through anything other than kicking their ass, but it wasn't built for
>> Roberts approach might be misguided, but I don't agree that having the
>> raw network data couldn't teach us something. E.g. have a look at this
>> guy who was able to identify the neurons responsible for generating URLs
>> in a wikipedia text generating RNN:
>> E.g. it might be possible to find the network Part of AlphaGo Zero which
>> is responsible for L&D problems and use it to dream up new Problems! The
>> possibilities could be endless. This kind of research might have been
>> easier with the "classic" AlphaGo with separated policy and value
>> networks, but should be possible anyways.
>> Also lets not forget DeepMinds own substantial research in this area:
>> I understand that DeepMind might be unable to release the source code of
>> AlphaGo due to policy or licensing reasons, but it would be great (and
>> probably much more valuable) if they could release the fully trained
>> network. As Gian-Carlo Pascutto has pointed out, replicating this would
>> not only incur high hardware costs but also take a long time.
>> David O.
>>> On Fri, Oct 20, 2017 at 8:24 AM, Robert Jasiek <jasiek at snafu.de
>>> <mailto:jasiek at snafu.de>> wrote:
>>> On 20.10.2017 15:07, Adrian.B.Robert at gmail.com
>>> <mailto:Adrian.B.Robert at gmail.com> wrote:
>>> 1) Where is the semantic translation of the neural net to
>>> human theory
>>> As far as (1), if we could do it, it would mean we could
>>> relate the
>>> structures embedded in the net's weight patterns to some other
>>> domain --
>>> The other domain can be "human go theory". It has various forms,
>>> from informal via textbook to mathematically proven. Sure, it is
>>> also incomplete but it can cope with additions.
>>> The neural net's weights and whatnot are given. This raw data can
>>> be deciphered in principle. By humans, algorithms or a combination.
>>> You do not know where to start? Why, that is easy: test! Modify
>>> ONE weight and study its effect on ONE aspect of human go theory,
>>> such as the occurrance (frequency) of independent life. No effect?
>>> Increase the modification, test a different weight, test a subset
>>> of adjacent weights etc. It has been possible to study semantics
>>> of parts of DNA, e.g., from differences related to illnesses.
>>> Modifications on the weights is like creating causes for illnesses
>>> (or improved health).
>>> There is no "we cannot do it", but maybe there is too much
>>> required effort for it to be financially worthwhile for the "too
>>> specialised" case of Go? As I say, a mathematical proof of a
>>> complete solution of Go will occur before AI playing perfectly;)
>>> So far neural
>>> nets have been trained and applied within single domains, and
>>> "generalization" means within that domain.
>>> robert jasiek
>>> Computer-go mailing list
>>> Computer-go at computer-go.org <mailto:Computer-go at computer-go.org>
>>> Computer-go mailing list
>>> Computer-go at computer-go.org
>> Computer-go mailing list
>> Computer-go at computer-go.org
>Diese E-Mail wurde von Avast Antivirus-Software auf Viren geprüft.
>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