GitHub Source, executable files. GitHub(Japanese top page)
2021-03-11 weight_decay(L2 regularization) is changed from 0.00004 to 0.0002. Back to original value. 34987k games, w3299.
2021-01-31 Drop the learning rate to 0.0000002. (from 30474k games, w3148).
2021-01-11 Replay buffer is past 1000000 games from past 500000 games. 28352k games, w3077.
2020-12-28 weight is updated from each 10000 games to 34285 games. 26700k games, w3022.
update history
In past hour, | number of clients are 3, | 5210 games. |
In past 24 hours, | number of clients are 6, | 105569 games. |
In past 1000 games, | Average of moves 88.5, | Sente winrate 0.544, | Draw rate 0.080 |
In past 1,000,000 games, | Average of moves 87.6, | Sente winrate 0.545, | Draw rate 0.222 |
AobaZero 800playouts/move vs Kristallweizen 500k/move. 800 match games.
You can see the transition of opening moves.
These are self-play games for training. It often plays blunder for the first 30 moves.
And sometimes it choose a move that is not a best by adding noise on root node.
From no000000000000.csa to no000000121031.csa are generated by not using neural network, but random function. The first game that is generated by neural network is no000000121032.csa no000001017999.csa. Up to here, 64x15block, window is past 100,000 games. no000001018000.csa. From here, 256x20block, window is past 500,000 games.Weights
w001 ... 64x15b,minibatch 64, learning rate 0.01, wd 0.00005, momentum 0.9, 120000 games w156 ... 64x15b,minibatch 64, learning rate 0.001, wd 0.00005, momentum 0.9, 430000 games w449 ... 256x20b,minibatch 64, learning rate 0.01, wd 0.0002, momentum 0.9, 1018000 games w465 ... 256x20b,minibatch 64, learning rate 0.001, wd 0.0002, momentum 0.9, 1180000 games w775 ... 256x20b,minibatch 4096, learning rate 0.02, wd 0.0002, momentum 0.9, 4220000 games w787 ... 256x20b,minibatch 128, learning rate 0.0002, wd 0.0002, momentum 0.9, 4340000 games w1450 ... 256x20b,minibatch 128, learning rate 0.00002, wd 0.0002, momentum 0.9, 10980000 games w2047 ... 256x20b,minibatch 128, learning rate 0.000002 ,wd 0.0002, momentum 0.9, 16948000 games w2750 ... 256x20b,minibatch 128, learning rate 0.000002 ,wd 0.00004, momentum 0.9, 23982000 games w3022 ... 256x20b,minibatch 128, learning rate 0.000002 ,wd 0.00004, momentum 0.9, 26706447 games w3077 ... 256x20b,minibatch 128, learning rate 0.000002 ,wd 0.00004, momentum 0.9, 28352543 games w3148 ... 256x20b,minibatch 128, learning rate 0.0000002,wd 0.00004, momentum 0.9, 30474874 games w3299 ... 256x20b,minibatch 128, learning rate 0.0000002,wd 0.0002, momentum 0.9, 34987582 games Weights are updated each 2000 games ( 4000 iterations) up to w448. Weights are updated each 10000 games (20000 iterations) from w449. Weights are updated each 10000 games (10000 iterations) from w787. Weights are updated each 34285 games (32000 iterations) from w3022. Replay buffer is past 1000000 games(from past 500000 games) from w3077.