More games in general. looks like more chess games than previously
available(wasn't it previously just 100, now it is 210)
and it looks like they addressed the flack they got from the chess
community by moving the hash size from 1G to 32G for stockfish.
On Thu, Dec 6, 2018 at 4:12 PM Rémi Coulom <remi.cou...@free.fr> wrote:
>
> Interesting, thanks. I had not found pseudocode.py.
>
> It is in that file:
> http://science.sciencemag.org/highwire/filestream/719481/field_highwire_adjunct_files/1/aar6404_DataS1.zip
>
> The link is at the bottom of that page:
> http://science.sciencemag.org/content/362/6419/1140/tab-figures-data
>
> Rémi
>
> ----- Mail original -----
> De: "Dan Schmidt" <d...@dfan.org>
> À: computer-go@computer-go.org
> Envoyé: Jeudi 6 Décembre 2018 23:39:57
> Objet: Re: [Computer-go] New paper by DeepMind
>
>
>
>
> I believe that the dependence of C(s) (formerly c_puct) on N(s) is new.
>
>
> The file pseudocode.py in the supplementary download sets c_base to 19652 and
> c_init to 1.25.
>
>
> Dan
>
>
>
> On Thu, Dec 6, 2018 at 5:27 PM Rémi Coulom < remi.cou...@free.fr > wrote:
>
>
> Hi,
>
> The new alphazero paper of DeepMind about chess and shogi has been published
> in Science:
>
> https://deepmind.com/blog/alphazero-shedding-new-light-grand-games-chess-shogi-and-go/
>
> pdf:
> https://deepmind.com/documents/260/alphazero_preprint.pdf
>
> I tried to play "spot the difference" with their previous draft, and did not
> notice any very important difference. They include shogi games, which might
> be appreciated by the shogi players. It seems they still don't tell the value
> of their exploration coefficient, unless I missed anything.
>
> Also, the AlphaZero algorithm is patented:
> https://patentscope2.wipo.int/search/en/detail.jsf?docId=WO2018215665
>
> Rémi
> _______________________________________________
> 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
