12
patrons
$45
per monthLeela developer/tester/enthusiast. Gauging interest on current projects. Working on supervised learning now with "Leelenstein", combined with some other lc0 branch things.
Leelenstein started out mostly CCRL games, with some 40b and T30 games. Currently uses CCRL games + more T30 games + SGDR + GGT + SE, but started with the same weights as the previous to retain some information from those other games.
(There have been several different SL runs with some nice nets picked from each, and some slightly different datasets.)
Trade Penalty is also recommended (and used at CCCC in current tournament).
SGDR is new method for learning rate scheduling.
https://arxiv.org/abs/1608.03983
GGT is new SL optimizer.
https://arxiv.org/pdf/1806.02958.pdf
Tested significantly stronger than Gull 3 on 30CPU with a 2080 TI, and beat the Sufi 32930 in a tactics test, but lost head to head.
Leelenstein started out mostly CCRL games, with some 40b and T30 games. Currently uses CCRL games + more T30 games + SGDR + GGT + SE, but started with the same weights as the previous to retain some information from those other games.
(There have been several different SL runs with some nice nets picked from each, and some slightly different datasets.)
Trade Penalty is also recommended (and used at CCCC in current tournament).
SGDR is new method for learning rate scheduling.
https://arxiv.org/abs/1608.03983
GGT is new SL optimizer.
https://arxiv.org/pdf/1806.02958.pdf
Tested significantly stronger than Gull 3 on 30CPU with a 2080 TI, and beat the Sufi 32930 in a tactics test, but lost head to head.
Tiers
Top Fan!
$5 or more per month (sold out!)
Show extra support. Possible exclusive posts, and access to network checkpoints at some LR cycle points. (When LR drops to zero). Preview of future performance that is possibly (but unlikely) stronger than final.
Leela developer/tester/enthusiast. Gauging interest on current projects. Working on supervised learning now with "Leelenstein", combined with some other lc0 branch things.
Leelenstein started out mostly CCRL games, with some 40b and T30 games. Currently uses CCRL games + more T30 games + SGDR + GGT + SE, but started with the same weights as the previous to retain some information from those other games.
(There have been several different SL runs with some nice nets picked from each, and some slightly different datasets.)
Trade Penalty is also recommended (and used at CCCC in current tournament).
SGDR is new method for learning rate scheduling.
https://arxiv.org/abs/1608.03983
GGT is new SL optimizer.
https://arxiv.org/pdf/1806.02958.pdf
Tested significantly stronger than Gull 3 on 30CPU with a 2080 TI, and beat the Sufi 32930 in a tactics test, but lost head to head.
Leelenstein started out mostly CCRL games, with some 40b and T30 games. Currently uses CCRL games + more T30 games + SGDR + GGT + SE, but started with the same weights as the previous to retain some information from those other games.
(There have been several different SL runs with some nice nets picked from each, and some slightly different datasets.)
Trade Penalty is also recommended (and used at CCCC in current tournament).
SGDR is new method for learning rate scheduling.
https://arxiv.org/abs/1608.03983
GGT is new SL optimizer.
https://arxiv.org/pdf/1806.02958.pdf
Tested significantly stronger than Gull 3 on 30CPU with a 2080 TI, and beat the Sufi 32930 in a tactics test, but lost head to head.
Recent posts by Jjosh
Tiers
Top Fan!
$5 or more per month (sold out!)
Show extra support. Possible exclusive posts, and access to network checkpoints at some LR cycle points. (When LR drops to zero). Preview of future performance that is possibly (but unlikely) stronger than final.