In the old days I trained separate move predictors on 9x9 games and on
19x19 games. In my case, the ones trained on 19x19 games beat the ones
trained on 9x9 games also on the 9x9 board. Perhaps it was just because of
was having better data from 19x19, but I thought it was interesting to see
that the 19x19 predictor generalized well to smaller boards.
I suppose the result you see can easily be explained; the big board policy
learns about large scale and small scale fights, while the small board
policy doesn't know anything about large scale fights.
On Fri, Feb 23, 2018 at 5:11 PM, Hiroshi Yamashita <y...@bd.mbn.or.jp> wrote:
> Using 19x19 policy on 9x9 and 13x13 is effective.
> But opposite is?
> I made 9x9 policy from Aya's 10k playout/move selfplay.
> Using 9x9 policy on 13x13 and 19x19
> 19x19 DCNNAyaF128from9x9 1799
> 13x13 DCNNAyaF128from9x9 1900
> 9x9 DCNN_AyaF128a558x1 2290
> Using 19x19 policy on 9x9 and 13x13
> 19x19 DCNN_AyaF128a523x1 2345
> 13x13 DCNNAya795F128a523 2354
> 9x9 DCNN_AyaF128a523x1 2179
> 19x19 policy is similar strength on 13x13 and 166 Elo weaker on 9x9.
> 9x9 policy is 390 Elo weaker on 13x13, and 491 Elo weaker on 19x19.
> It seems smaller board is more useless than bigger board...
> All programs select maximum policy without search.
> All programs use opening book.
> 19x19 policy is Filter128, Layer 12, without Batch Normalization.
> 9x9 policy is Filter128, Layer 11, without Batch Normalization.
> 19x19 policy is made from pro 78000 games, GoGoD.
> 9x9 policy is made from 10k/move. It is CGOS 2892(Aya797c_p1v1_10k).
> Ratings are BayesElo.
> Hiroshi Yamashita
> Computer-go mailing list
Computer-go mailing list