Finished
VshcheIgelsingular-killer-suppressiondiff10.0+0.10LLR: 2.98 (-2.94, 2.94) [0.00, 2.00]
Games: 87476 W: 21987 L: 21564 D: 43925
Ptnml(0-2): 618, 10518, 21048, 10931, 623
3.6.36: skip killer moves for skipmoves
KierenHalogenspsa_tune_21_50kdiff5.0+0.05LLR: 2.95 (-2.94, 2.94) [0.00, 3.00]
Games: 23702 W: 6083 L: 5860 D: 11759
Ptnml(0-2): 58, 2638, 6236, 2861, 58
KierenHalogenspsa_tune_21_50kdiff40.0+0.40LLR: 2.96 (-2.94, 2.94) [0.00, 3.00]
Games: 18562 W: 4662 L: 4454 D: 9446
Ptnml(0-2): 27, 2034, 4945, 2254, 21
RosentWintermaster *diff40.0+0.40Elo: 26.89 +- 6.25 (95%) [N=4000]
Games: 4000 W: 1002 L: 693 D: 2305
Ptnml(0-2): 33, 354, 963, 571, 79
Regression Test vs v5.0
RosentWinternet311_ace501v2 *diff40.0+0.40LLR: 2.95 (-2.94, 2.94) [0.00, 5.00]
Games: 7672 W: 1608 L: 1462 D: 4602
Ptnml(0-2): 83, 791, 1949, 923, 90
This is also trained with WSD but more data. I think I need to train with a longer cooldown phase and have a run with the old scheduler which will hopefully finish this afternoon.
KierenHalogenspsa_tune_21_50kdiff8.0+0.08LLR: 2.95 (-2.94, 2.94) [0.00, 3.00]
Games: 28958 W: 7581 L: 7334 D: 14043
Ptnml(0-2): 147, 3324, 7306, 3539, 163
VshcheIgelnmsdiff60.0+0.60LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 16098 W: 3903 L: 3621 D: 8574
Ptnml(0-2): 30, 1766, 4178, 2042, 33
3.6.35: stake piece stack for nmp
VshcheIgelepdiff10.0+0.10LLR: 3.00 (-2.94, 2.94) [-3.00, 1.00]
Games: 123686 W: 30185 L: 30236 D: 63265
Ptnml(0-2): 812, 14592, 31031, 14651, 757
3.6.36: handle ep tb moves
RosentWinternet311_ace501v2 *diff8.0+0.08LLR: 3.02 (-2.94, 2.94) [0.00, 5.00]
Games: 19066 W: 4895 L: 4667 D: 9504
Ptnml(0-2): 418, 2294, 3920, 2444, 457
This is also trained with WSD but more data. I think I need to train with a longer cooldown phase and have a run with the old scheduler which will hopefully finish this afternoon.
VshcheIgelnmsdiff10.0+0.10LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 56094 W: 14147 L: 13774 D: 28173
Ptnml(0-2): 408, 6688, 13503, 7019, 429
3.6.35: stake piece stack for nmp
VshcheIgeltt_replacediff60.0+0.60LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 18256 W: 4405 L: 4117 D: 9734
Ptnml(0-2): 33, 2089, 4597, 2375, 34
3.6.35: improve TT replace strategy
VshcheIgeltt_replacediff10.0+0.10LLR: 2.97 (-2.94, 2.94) [0.00, 2.00]
Games: 39844 W: 10115 L: 9768 D: 19961
Ptnml(0-2): 290, 4668, 9673, 4987, 304
3.6.35: improve TT replace strategy
VshcheIgeldse2diff10.0+0.10LLR: 2.97 (-2.94, 2.94) [0.00, 2.00]
Games: 141032 W: 35221 L: 34716 D: 71095
Ptnml(0-2): 962, 17018, 34108, 17409, 1019
3.6.35: bigger beta cut condition - after rebase
TerjeWeissBBFunctionsdiffN=25000Elo: -0.00 +- 0.00 (95%) [N=40000]
Games: 41472 W: 14978 L: 14978 D: 11516
Ptnml(0-2): 0, 0, 20736, 0, 0
VshcheIgeliiddiff10.0+0.10LLR: 2.98 (-2.94, 2.94) [0.00, 2.00]
Games: 61934 W: 15610 L: 15227 D: 31097
Ptnml(0-2): 380, 7557, 14828, 7704, 498
3.6.34: simplified IID
VshcheIgelsingular_search_plydiff60.0+0.60LLR: 3.00 (-2.94, 2.94) [0.00, 2.00]
Games: 31258 W: 7418 L: 7107 D: 16733
Ptnml(0-2): 55, 3638, 7964, 3885, 87
3.6.33: singular search ply coherence
VshcheIgelsingular_search_plydiff10.0+0.10LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 130300 W: 32600 L: 32110 D: 65590
Ptnml(0-2): 914, 15801, 31292, 16167, 976
3.6.33: singular search ply coherence
VshcheIgelstandpat_ttdiff10.0+0.10LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 71352 W: 17824 L: 17431 D: 36097
Ptnml(0-2): 480, 8546, 17287, 8827, 536
3.6.33: fix tt depth in stand pat
VshcheIgelhist_guarddiff10.0+0.10LLR: 3.01 (-2.94, 2.94) [-3.00, 1.00]
Games: 73954 W: 18457 L: 18431 D: 37066
Ptnml(0-2): 482, 8651, 18676, 8695, 473
3.6.32: fix UB
TerjeWeissBackwardUnopposedPawns2diff60.0+0.60LLR: 2.96 (-2.94, 2.94) [0.00, 3.00]
Games: 153080 W: 40252 L: 39701 D: 73127
Ptnml(0-2): 1136, 18242, 37232, 18795, 1135
VshcheIgelfix_undo3diff10.0+0.10LLR: 2.98 (-2.94, 2.94) [-3.00, 1.00]
Games: 9284 W: 2386 L: 2262 D: 4636
Ptnml(0-2): 58, 1017, 2386, 1105, 76
3.6.31: fix undo bug
RosentWinternet311_ace501 *diff40.0+0.40LLR: 2.97 (-2.94, 2.94) [-5.00, 0.00]
Games: 15212 W: 2871 L: 2820 D: 9521
Ptnml(0-2): 109, 1621, 4104, 1654, 118
New approach to training net. Hopefully at least Elo neutral but less blunder prone.
VshcheIgelfutility_inheckdiff2.5+0.03LLR: 2.99 (-2.94, 2.94) [0.00, 2.00]
Games: 5710 W: 1781 L: 1438 D: 2491
Ptnml(0-2): 91, 575, 1229, 820, 140
3.6.29: apply incheck futility guard
VshcheIgelfutility_inheckdiff60.0+0.60LLR: 2.95 (-2.94, 2.94) [-3.00, 1.00]
Games: 21074 W: 4949 L: 4850 D: 11275
Ptnml(0-2): 38, 2496, 5362, 2611, 30
3.6.29: apply incheck futility guard
RosentWinternet311_ace501 *diff8.0+0.08LLR: 2.95 (-2.94, 2.94) [-5.00, 0.00]
Games: 56412 W: 13466 L: 13594 D: 29352
Ptnml(0-2): 1179, 6842, 12275, 6748, 1162
New approach to training net. Hopefully at least Elo neutral but less blunder prone.