Closed l1t1 closed 3 years ago
It's explained in the Telegram channel (link in SAI homepage). Current experiment are networks trained with KLE loss (cross-entropy) instead of MSE loss (difference squared) for the value head. Four nets are trained for each generation, starting from the previous best KLE network. (We make a small number of matches with low visits to get a reasonable evaluation of strength.) The experiment will be evaluated after 10 generations, and we are at 7. Previously we had a huge factorial experiment in training 20x256 networks at generation g1a8 (SAI424). Results were appalling though, because no matter what we changed, we could not get networks clearly stronger than the same generation's 12x256.
thanks, the Telegram channel is banned in my area
Oh, I am sorry about that. Maybe someone can find a way around to put the same content in a reachable place?
this net (779e82d7) seems very strong, could you promote it force?
779e82d7 VS 79cec3c4 | 18 : 2 : 5 (76.00%) |
---|
It is a KLE network. Surely it is strong, but its current Elo is overestimated because no subsequent network was tested against it.
Anyway we will be passing to KLE training in a few days. (Sorry, but I have to prepare a conference.)
and how the games of each type be decided?