[Computer-go] New paper by DeepMind
dshawul at gmail.com
Thu Dec 6 15:26:19 PST 2018
What exactly is the innovation that is patented ?
Using short look-ahead searches for tuning evaluation functions ( in this
case a neural network ) is not exactly new.
On Thu, Dec 6, 2018 at 3:28 PM Rémi Coulom <remi.coulom at free.fr> wrote:
> The new alphazero paper of DeepMind about chess and shogi has been
> published in Science:
> 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:
> Computer-go mailing list
> Computer-go at computer-go.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Computer-go