[Computer-go] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Roel van Engelen
gosubaduk at gmail.com
Tue Dec 19 08:49:25 PST 2017
>I was thinking about this development and what it may mean from the point
of view of a more general AI.
>I daresay the next experiment would be to have just one neural net playing
the >three games, right?
>To my understanding we still have three instances of the same *methodology* but
not yet a single one playing different games.
Deepmind did some research on that topic with the atari games:
and yes what you describe would be a more general AI but it would be more
interesting to include all 48 atari games
from previous research as well, although i suspect a real general AI will
be developed from a different line of research
as for what Deepmind will be researching, always a guess but i think we
will hear more about tabula rasa stuff since several
real world problems like the salesman problem
<http://www.diego-perez.net/papers/MCTS_PTSP.pdf> have been adapted to be
solved with mcts.
But we will have to wait for their next paper/blog to know for sure.
On 19 December 2017 at 16:15, Fidel Santiago <pperez333 at gmail.com> wrote:
> I was thinking about this development and what it may mean from the point
> of view of a more general AI. I daresay the next experiment would be to
> have just one neural net playing the three games, right? To my
> understanding we still have three instances of the same *methodology* but
> not yet a single one playing different games.
> Best regards,
> Fidel Santiago.
> Computer-go mailing list
> Computer-go at computer-go.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Computer-go