[Computer-go] Aya reaches pro level on GoQuest 9x9 and 13x13
Roel van Engelen
ich.bun.ut at gmail.com
Sat Nov 19 08:53:46 PST 2016
My bot is not pro jet but i build gosu games
similar to waltheri.net <http://ps.waltheri.net/> ) and i found certain
occurring in 200+ games where over 80% of the pro's chooses move A while
90% of the games picking move A is
lost by that player.
suggesting pro players in certain positions choose a "sub optimal" move
to me it seems that the influence of these "sub optimal" moves is
diminished by using reinforcement learning for a
limited time, unfortunately my implementation is not ready enough to verify
On 19 November 2016 at 09:07, Detlef Schmicker <ds2 at physik.de> wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
> Hi Hiroshi,
> thanks a lot for your info.
> You did not try reinforcement learning I think. Do you have any idea,
> why this would make the policy network 250ELO stronger, as mentioned
> in the alphago paper (80% winrate)?
> Are pros playing so bad?
> Do you think playing strength would be better, if one only takes into
> account the moves of the winning player?
> Am 19.11.2016 um 05:18 schrieb Hiroshi Yamashita:
> > Hi,
> >> Did you not find a benefit from a larger value network? Too
> >> little data and too much overfitting? Or more benefit from more
> >> frequent evaluation?
> > I did not find larger value network is better. But I think I need
> > more taraining data and stronger selfplay. I did not find
> > overfitting so far, and did not try more frequent evaluation.
> >>> Policy + Value vs Policy, 1000 playouts/move, 1000 games. 9x9,
> >>> komi 7.0 0.634 using game result. 0 or 1
> >> I presume this is a winrate, but over what base? Policy network?
> > Yes. Policy network(only root node) + value network vs Policy
> > network(only root node).
> >> How do you handle handicap games? I see you excluded them from
> >> the KGS dataset. Can your value network deal with handicap?
> > I excluded hadicap games. My value network can not handle hadicaps.
> > It it only for komi 7.5.
> > Thanks, Hiroshi Yamashita
> > _______________________________________________ Computer-go mailing
> > list Computer-go at computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v2.0.22 (GNU/Linux)
> -----END PGP SIGNATURE-----
> Computer-go mailing list
> Computer-go at computer-go.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Computer-go