Finished | ||||||
---|---|---|---|---|---|---|
Peregr | Integral | [Reckless] main | diff | 40.0+0.40 | Elo: 38.72 +- 5.01 (95%) [N=10000] Games: 4730 W: 1513 L: 988 D: 2229 Ptnml(0-2): 15, 330, 1143, 869, 8 | Old PT |
Styxdo | Reckless | weights_s1_v25_s2_equal | diff | 8.0+0.08 | LLR: -2.26 (-2.25, 2.89) [0.00, 4.00] Games: 6152 W: 1475 L: 1558 D: 3119 Ptnml(0-2): 16, 792, 1549, 697, 22 | Same S1 as v25, S2 equal weights for 640 and 1536 |
Styxdo | Reckless | weights_s1_v25_s2_equal | diff | N=25000 | LLR: -2.33 (-2.25, 2.89) [0.00, 4.00] Games: 11852 W: 3838 L: 3934 D: 4080 Ptnml(0-2): 443, 1325, 2454, 1293, 411 | Same S1, S2 same weight for 640 and 1536 |
World | Reckless | fp-null-move | diff | 8.0+0.08 | LLR: -2.28 (-2.25, 2.89) [0.00, 4.00] Games: 33692 W: 8158 L: 8160 D: 17374 Ptnml(0-2): 111, 4112, 8408, 4098, 117 | |
World | Reckless | reset-optimizer-with-warmup | diff | 8.0+0.08 | LLR: -2.28 (-2.25, 2.89) [0.00, 4.00] Games: 22370 W: 5378 L: 5414 D: 11578 Ptnml(0-2): 78, 2725, 5622, 2675, 85 | |
World | Reckless | see-threshold-test | diff | 8.0+0.08 | LLR: -2.34 (-2.25, 2.89) [0.00, 4.00] Games: 4934 W: 1156 L: 1248 D: 2530 Ptnml(0-2): 20, 651, 1212, 569, 15 | |
World | Reckless | see-threshold | diff | 40.0+0.40 | Tuning 15 Parameters 7511/7500 Iterations 15022/15000 Games Played | |
World | Reckless | futility-value-mc | diff | 8.0+0.08 | LLR: -2.27 (-2.25, 2.89) [0.00, 4.00] Games: 7674 W: 1791 L: 1870 D: 4013 Ptnml(0-2): 24, 972, 1918, 905, 18 | |
Peregr | Reckless | ergodice_stuff | diff | 8.0+0.08 | LLR: -2.36 (-2.25, 2.89) [0.00, 4.00] Games: 19496 W: 4641 L: 4689 D: 10166 Ptnml(0-2): 63, 2388, 4908, 2312, 77 | check ergodice idea |
World | Reckless | ergodice_stuff_fast_unsound | diff | 8.0+0.08 | LLR: -2.33 (-2.25, 2.89) [0.00, 4.00] Games: 7680 W: 1840 L: 1923 D: 3917 Ptnml(0-2): 36, 974, 1890, 917, 23 | |
Peregr | Reckless | less-tt-cut | diff | 8.0+0.08 | LLR: -2.31 (-2.25, 2.89) [0.00, 4.00] Games: 32864 W: 7907 L: 7913 D: 17044 Ptnml(0-2): 132, 3915, 8319, 3959, 107 | less ~14% |
World | Reckless | lmr-iir | diff | 8.0+0.08 | LLR: -2.29 (-2.25, 2.89) [0.00, 4.00] Games: 16084 W: 3891 L: 3947 D: 8246 Ptnml(0-2): 79, 1946, 4027, 1932, 58 | |
World | Reckless | lmp-static-eval | diff | 8.0+0.08 | LLR: 3.04 (-2.25, 2.89) [0.00, 4.00] Games: 22280 W: 5555 L: 5350 D: 11375 Ptnml(0-2): 89, 2592, 5570, 2803, 86 | |
World | Reckless | conthist-spsa-results | diff | 8.0+0.08 | LLR: -2.34 (-2.25, 2.89) [0.00, 4.00] Games: 20550 W: 4890 L: 4934 D: 10726 Ptnml(0-2): 75, 2474, 5219, 2434, 73 | |
World | Reckless | conthist-spsa | diff | 8.0+0.08 | Tuning 2 Parameters 3915/4000 Iterations 7830/8000 Games Played | what are the chances spsa works for 2 params? |
Styxdo | Reckless | v25-f71908d1 | diff | 40.0+0.40 | LLR: 2.89 (-2.25, 2.89) [0.00, 4.00] Games: 31488 W: 7463 L: 7250 D: 16775 Ptnml(0-2): 28, 3602, 8267, 3823, 24 | S1 Higher weight to 640, S2 higher weight to 1536 (S1: 640=1, 1536 =0.5 S2: 640=0.5, 1536=1) |
World | Reckless | reset-optimizer-with-warmup | diff | N=25000 | LLR: -2.44 (-2.25, 2.89) [0.00, 4.00] Games: 3090 W: 952 L: 1091 D: 1047 Ptnml(0-2): 129, 375, 646, 296, 99 | Replace loading the AdamW optimizer state into S2 with warmup batches |
Peregr | Reckless | fp-hist | diff | 8.0+0.08 | LLR: -2.01 (-2.25, 2.89) [0.00, 4.00] Games: 21914 W: 5248 L: 5273 D: 11393 Ptnml(0-2): 81, 2611, 5598, 2586, 81 | |
World | Reckless | v25-f71908d1 | diff | N=25000 | LLR: -2.30 (-2.25, 2.89) [0.00, 4.00] Games: 34034 W: 11320 L: 11323 D: 11391 Ptnml(0-2): 1274, 3725, 7021, 3724, 1273 | S1 Higher weight to 640, S2 higher weight to 1536 (S1: 640=1, 1536 =0.5 S2: 640=0.5, 1536=1) |
Styxdo | Reckless | v25-f71908d1 | diff | 8.0+0.08 | LLR: 2.96 (-2.25, 2.89) [0.00, 4.00] Games: 11194 W: 2845 L: 2675 D: 5674 Ptnml(0-2): 45, 1291, 2764, 1443, 54 | S1 Higher weight to 640, S2 higher weight to 1536 (S1: 640=1, 1536 =0.5 S2: 640=0.5, 1536=1) |
World | Reckless | s1_lr_warmup | diff | N=25000 | LLR: -2.38 (-2.25, 2.89) [0.00, 4.00] Games: 38400 W: 12811 L: 12801 D: 12788 Ptnml(0-2): 1423, 4195, 7967, 4179, 1436 | LR Warmup over 1024 batches |
Peregr | Reckless | simpl-fp | diff | 40.0+0.40 | LLR: 2.91 (-2.25, 2.89) [-4.00, 0.00] Games: 31120 W: 7186 L: 7150 D: 16784 Ptnml(0-2): 20, 3594, 8304, 3614, 28 | |
Styxdo | Reckless | s1_lr_warmup | diff | 8.0+0.08 | LLR: -2.25 (-2.25, 2.89) [0.00, 4.00] Games: 27434 W: 6827 L: 6847 D: 13760 Ptnml(0-2): 121, 3372, 6770, 3314, 140 | LR Warmup over 1024 batches |
Peregr | Reckless | simpl-fp | diff | 8.0+0.08 | LLR: 2.97 (-2.25, 2.89) [-4.00, 0.00] Games: 15518 W: 3830 L: 3742 D: 7946 Ptnml(0-2): 63, 1837, 3857, 1953, 49 | use the new values, but need to run LTC for this as well |
Peregr | Reckless | simpl-fp | diff | 8.0+0.08 | LLR: -0.43 (-2.25, 2.89) [-3.00, 0.00] Games: 5598 W: 1357 L: 1395 D: 2846 Ptnml(0-2): 16, 696, 1421, 642, 24 |