Lc0 saturation.

[stavros]

after 37 million games i didnt see any saturation ,maybe that network is better than A0?
can anyone explain this?

[frankp]

I certainly cannot comment on the question.
Practically, they would would have to run leela on the same hardware as A0 to know. Although scaling arguments (the leela ratio) have been made on the leela forum to suggest it is not there yet, but also not very far away.
IIRC, David Silver in one of his lectures indicated that A0 was still getting stronger when they stopped the A0 (Go, chess, shogi) training. So it seems A0 could have been, or could be, made even stronger. Their publically stated goal was to demonstrate the potential of their AI approach in these closed systems and that goal had been achieved, so they stopped - apparently.

[Uri Blass]

after 37 million games i didnt see any saturation ,maybe that network is better than A0?
can anyone explain this?

A0 scaled better than stockfish8 based on what I read(lost against stockfish at fast time control only to win at longer time control).
Does lc0 scale better than stockfish8?

If not then it seems that lc0 and A0 do not do the same thing.

[jp]

IIRC, David Silver in one of his lectures indicated that A0 was still getting stronger when they stopped the A0 (Go, chess, shogi) training. So it seems A0 could have been, or could be, made even stronger. Their publically stated goal was to demonstrate the potential of their AI approach in these closed systems and that goal had been achieved, so they stopped - apparently.

No, it was supposedly still getting better for Go, not for chess. Their figure showed it had flatlined for chess after about 12 million games. Or 21 million if you want to be cautious.

[stavros]

what i mean saturation is lower elo gain per week for example until no further improving

[Leo]

I think it is saturated.

[stavros]

from testserver.lczero.org there is a lot regression, see from 10854 to 10879
http://testserver.lczero.org/matches

[whereagles]

it will eventually saturate the 20x256 NN.. might saturate at a higher ELO with a bigger net, but that's not clear

as of now saturation can be checked for with some statistical time-series test, but just from looking at it, I doubt it reached that point.

[JJJ]

I heard bigger net was coming anyway. I don't think Lczero will reach the level of the big 3 with this size of net, but it might with the next one. Anyway, in one year, Lczero will be the best engine in the world.

[Leo]

I heard bigger net was coming anyway. I don't think Lczero will reach the level of the big 3 with this size of net, but it might with the next one. Anyway, in one year, Lczero will be the best engine in the world.

When?