| Active : 2 Machines / 39 Threads / 18.29 MNPS | ||||||
|---|---|---|---|---|---|---|
| Priority 0 | ||||||
| Dseker | BlackMarlin | major-overhaul | diff | 8.0+0.08 | LLR: 2.04 (-2.94, 2.94) [-4.00, 0.00] Games: 18748 W: 4661 L: 4623 D: 9464 Ptnml(0-2): 123, 2252, 4616, 2230, 153 | Fix best move printing |
| Vshche | Igel | tune-group-b-v3 | diff | 10.0+0.10 | Tuning 60 Parameters 2754/25000 Iterations 44068/400000 Games Played | |
| Priority -1 | ||||||
| Dseker | BlackMarlin | movegen-depth-see | diff | 8.0+0.08 | LLR: -0.16 (-2.94, 2.94) [0.00, 4.00] Games: 93454 W: 23178 L: 22896 D: 47380 Ptnml(0-2): 595, 10980, 23310, 11232, 610 | depth based see margin for good captures in move gen |
| Dseker | BlackMarlin | lmr-combined | diff | 8.0+0.08 | LLR: -1.53 (-2.94, 2.94) [0.00, 4.00] Games: 43980 W: 10993 L: 10928 D: 22059 Ptnml(0-2): 293, 5206, 10959, 5207, 325 | Reduce more when all 3 reduction conditions are met |
| Dseker | BlackMarlin | simplify-killer-lmr | diff | 40.0+0.40 | LLR: -1.80 (-2.94, 2.94) [-4.00, 0.00] Games: 46366 W: 11168 L: 11378 D: 23820 Ptnml(0-2): 103, 5417, 12334, 5245, 84 | Simplify killer LMR |
| Dseker | BlackMarlin | movegen-depth-capture-value | diff | 8.0+0.08 | LLR: -2.11 (-2.94, 2.94) [0.00, 4.00] Games: 13624 W: 3381 L: 3437 D: 6806 Ptnml(0-2): 94, 1592, 3487, 1554, 85 | Disregard the value of captured pieces in movegen at higher depths |
| Priority -5 | ||||||
| Terje | Weiss | Connectivity2 | diff | 60.0+0.60 | LLR: -0.21 (-2.94, 2.94) [0.00, 3.00] Games: 68704 W: 17741 L: 17594 D: 33369 Ptnml(0-2): 461, 8109, 17058, 8270, 454 | |
| Finished | ||||||
| Mhoupp | Stash | draw_score_granularity | diff | 8.0+0.08 | LLR: -3.01 (-2.94, 2.94) [0.00, 5.00] Games: 58234 W: 14561 L: 14438 D: 29235 Ptnml(0-2): 692, 7100, 13473, 7097, 755 | Make the randomized draw score more granular |
| Dseker | BlackMarlin | major-overhaul | diff | 8.0+0.08 | LLR: 0.00 (-2.94, 2.94) [-4.00, 0.00] Games: 0 W: 0 L: 0 D: 0 Ptnml(0-2): 0, 0, 0, 0, 0 | Fix makefile? |
| Dseker | BlackMarlin | major-overhaul | diff | 8.0+0.08 | LLR: 0.00 (-2.94, 2.94) [-4.00, 0.00] Games: 0 W: 0 L: 0 D: 0 Ptnml(0-2): 0, 0, 0, 0, 0 | Switch to thin LTO |
| Connor | Seer | non-pawn-correction-history | diff | 40.0+0.40 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 68910 W: 16859 L: 16544 D: 35507 Ptnml(0-2): 103, 7798, 18352, 8085, 117 | test |
| Vshche | Igel | shared_hist2 | diff | 20.0+0.20 | LLR: 0.07 (-2.94, 2.94) [0.00, 2.00] Games: 1072 W: 280 L: 273 D: 519 Ptnml(0-2): 0, 115, 299, 122, 0 | 3.8.11: shared history |
| Vshche | Igel | shared_hist2 | diff | 5.0+0.05 | LLR: 2.96 (-2.94, 2.94) [0.00, 2.00] Games: 16094 W: 4216 L: 3940 D: 7938 Ptnml(0-2): 14, 1760, 4225, 2032, 16 | 3.8.11: shared history |
| Dseker | Stash | no_goto_when_in_check | diff | 40.0+0.40 | LLR: 2.96 (-2.94, 2.94) [-4.00, 1.00] Games: 27924 W: 6510 L: 6465 D: 14949 Ptnml(0-2): 140, 3285, 7084, 3296, 157 | Don't use a goto to reach the main search loop when in check |
| Dseker | BlackMarlin | nmp-eval-increase | diff | 8.0+0.08 | LLR: -1.91 (-2.94, 2.94) [0.00, 4.00] Games: 18270 W: 4449 L: 4482 D: 9339 Ptnml(0-2): 120, 2203, 4532, 2150, 130 | early stop NMP if eval after null move is better than eval before |
| Dseker | BlackMarlin | nmp-eval-increase-2 | diff | 8.0+0.08 | LLR: -1.39 (-2.94, 2.94) [0.00, 4.00] Games: 8752 W: 2144 L: 2182 D: 4426 Ptnml(0-2): 55, 1066, 2172, 1028, 55 | early stop NMP if eval after null move is better than eval before (take 2) |
| Dseker | BlackMarlin | nmp-eval-increase-3 | diff | 40.0+0.40 | LLR: 2.95 (-2.94, 2.94) [0.00, 4.00] Games: 7914 W: 1999 L: 1850 D: 4065 Ptnml(0-2): 10, 841, 2120, 962, 24 | early stop NMP if eval after null move is better than eval before (take 3) |
| Vshche | Igel | nn-epoch999 * | diff | 60.0+0.60 | LLR: 2.96 (-2.94, 2.94) [0.00, 2.00] Games: 3392 W: 885 L: 614 D: 1893 Ptnml(0-2): 4, 293, 838, 550, 11 | test against frc net |
| Dseker | BlackMarlin | nmp-eval-increase-3 | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [0.00, 4.00] Games: 101338 W: 25264 L: 24811 D: 51263 Ptnml(0-2): 642, 11874, 25263, 12169, 721 | early stop NMP if eval after null move is better than eval before (take 3) |
| Vshche | Igel | numa | diff | 90.0+0.90 | LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 44568 W: 11399 L: 11089 D: 22080 Ptnml(0-2): 16, 4999, 11940, 5317, 12 | numa + new net - VLTC - TBC |
| Mhoupp | Stash | no_goto_when_in_check | diff | 8.0+0.08 | LLR: 3.07 (-2.94, 2.94) [-4.00, 1.00] Games: 5800 W: 1545 L: 1432 D: 2823 Ptnml(0-2): 80, 652, 1334, 743, 91 | Don't use a goto to reach the main search loop when in check |
| Vshche | Igel | shared_hist | diff | 5.0+0.05 | LLR: -0.21 (-2.94, 2.94) [0.00, 2.00] Games: 4942 W: 1237 L: 1248 D: 2457 Ptnml(0-2): 4, 589, 1293, 584, 1 | 3.8.10: shared history |
| Dseker | BlackMarlin | quiet-bad-cap-lmr-2 | diff | 8.0+0.08 | LLR: -3.05 (-2.94, 2.94) [0.00, 4.00] Games: 4676 W: 1097 L: 1222 D: 2357 Ptnml(0-2): 25, 611, 1185, 498, 19 | More LMR for quiet moves and bad captures excluding killers |
| Vshche | Igel | hist_cap | diff | 10.0+0.10 | LLR: -1.08 (-2.94, 2.94) [-3.00, 1.00] Games: 34894 W: 8906 L: 9003 D: 16985 Ptnml(0-2): 69, 4118, 9182, 3997, 81 | 3.8.9: cap history bonus |
| Rosent | Winter | wider_hidden * | diff | 8.0+0.08 | LLR: -2.97 (-2.94, 2.94) [0.00, 5.00] Games: 6878 W: 1700 L: 1804 D: 3374 Ptnml(0-2): 180, 862, 1445, 786, 166 | This network has a larger hidden layer. This is unlikely to be worth the overhead at this point. |
| Vshche | Igel | hist_cap | diff | 60.0+0.60 | LLR: 2.96 (-2.94, 2.94) [-3.00, 1.00] Games: 27862 W: 7027 L: 6942 D: 13893 Ptnml(0-2): 7, 3124, 7590, 3197, 13 | 3.8.9: cap history bonus |
| Vshche | Igel | B61B92877D7AD253 | diff | 1.0+0.01 | LLR: 2.97 (-2.94, 2.94) [-3.00, 1.00] Games: 6230 W: 1735 L: 1613 D: 2882 Ptnml(0-2): 15, 681, 1605, 795, 19 | 3.8.8: calculate nodes share per move |
| Connor | Seer | non-pawn-correction-history | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 25588 W: 6411 L: 6170 D: 13007 Ptnml(0-2): 150, 2905, 6452, 3128, 159 | test |
| Vshche | Igel | nodes_share | diff | 60.0+0.60 | LLR: 2.95 (-2.94, 2.94) [0.00, 2.00] Games: 17598 W: 4622 L: 4351 D: 8625 Ptnml(0-2): 7, 1874, 4772, 2133, 13 | 3.8.8: calculate nodes share per move |
| Jhonno | Berserk | exp/h640 | diff | 60.0+0.60 | LLR: -2.25 (-2.25, 2.89) [0.00, 2.50] Games: 7762 W: 1894 L: 2032 D: 3836 Ptnml(0-2): 12, 936, 2116, 812, 5 | 0052: N_HIDDEN 640 (main recipe, two stages) vs main net; 128-lane accumulator tiles. Fixed 40k nodes +6.73 +/- 3.23, SPRT [0, 2.5] passed (16,471 games) |
| Vshche | Igel | nodes_share | diff | 10.0+0.10 | Elo: 45.85 +- 6.19 (95%) [N=40000] Games: 3308 W: 1082 L: 648 D: 1578 Ptnml(0-2): 10, 227, 753, 647, 17 | Regression peek |
| Vshche | Igel | nodes_share | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [0.00, 2.00] Games: 18420 W: 4996 L: 4713 D: 8711 Ptnml(0-2): 32, 2017, 4843, 2272, 46 | 3.8.8: calculate nodes share per move |