Finished
RosentWinterqnet_422_d32 *diff8.0+0.08LLR: 2.98 (-2.94, 2.94) [-1.00, 4.00]
Games: 16562 W: 3975 L: 3799 D: 8788
Ptnml(0-2): 292, 1970, 3657, 1994, 368
Updated network. Slightly more lax bounds to ensure we make it in time for the TCEC submission.
VshcheIgelcapture_history_rebaseddiff60.0+0.60LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 13520 W: 3375 L: 3102 D: 7043
Ptnml(0-2): 12, 1467, 3535, 1728, 18
3.7.9: implement capture history
VshcheIgelcapture_history_rebaseddiff10.0+0.10LLR: 2.98 (-2.94, 2.94) [0.00, 2.00]
Games: 39720 W: 10070 L: 9739 D: 19911
Ptnml(0-2): 156, 4664, 9889, 4995, 156
3.7.9: implement capture history
RosentWintermove_order_bugfix *diff40.0+0.40LLR: 2.95 (-2.94, 2.94) [-4.00, 1.00]
Games: 6020 W: 1159 L: 1064 D: 3797
Ptnml(0-2): 40, 628, 1593, 695, 54
Fixed move ordering bug where history heuristics were ignored if previous move was a null move.
VshcheIgelcache-accumulatordiff10.0+0.10LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 6870 W: 1860 L: 1587 D: 3423
Ptnml(0-2): 16, 694, 1747, 957, 21
3.7.8: cache accumulator
VshcheIgelcapture_historydiff10.0+0.10LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 42658 W: 10896 L: 10563 D: 21199
Ptnml(0-2): 153, 5050, 10611, 5341, 174
3.7.8: implement capture history (STC)
RosentWintermove_order_bugfix *diff8.0+0.08LLR: 2.95 (-2.94, 2.94) [-4.00, 1.00]
Games: 11914 W: 2756 L: 2661 D: 6497
Ptnml(0-2): 199, 1398, 2699, 1431, 230
Restarted the test as a non-regression patch. It is unclear how much Elo the change should be worth, but it is the more reasonable form, so it should be added even if Elo neutral or slightly negative.
VshcheIgeladaptive-lmrdiff60.0+0.60LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 13160 W: 3342 L: 3068 D: 6750
Ptnml(0-2): 12, 1445, 3395, 1713, 15
3.7.7: implement adaptive lmr (LTC)
VshcheIgeladaptive-lmrdiff10.0+0.10LLR: 2.97 (-2.94, 2.94) [0.00, 2.00]
Games: 24046 W: 6257 L: 5947 D: 11842
Ptnml(0-2): 119, 2749, 5974, 3065, 116
3.7.7: implement adaptive lmr (STC)
VshcheIgelcorrection3-tuned-adiff60.0+0.60LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 9636 W: 2442 L: 2174 D: 5020
Ptnml(0-2): 5, 1025, 2497, 1279, 12
3.7.6: tuned correction history (LTC)
VshcheIgelcorrection3-tuned-adiff10.0+0.10LLR: 2.97 (-2.94, 2.94) [0.00, 2.00]
Games: 11138 W: 2962 L: 2670 D: 5506
Ptnml(0-2): 40, 1241, 2751, 1461, 76
3.7.6: tuned correction history (STC)
VshcheIgel6b953e78.standarddiff90.0+0.90LLR: 2.97 (-2.94, 2.94) [0.00, 2.00]
Games: 4692 W: 1278 L: 1011 D: 2403
Ptnml(0-2): 4, 442, 1188, 707, 5
new network - take #2 (VLTC)
RosentWinterqnet_402_d32 *diff40.0+0.40Elo: 71.79 +- 6.17 (95%) [N=4000]
Games: 4000 W: 1273 L: 458 D: 2269
Ptnml(0-2): 12, 185, 915, 752, 136
Regression test vs v5.0
VshcheIgel6b953e78.standarddiff60.0+0.60LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 4840 W: 1283 L: 1015 D: 2542
Ptnml(0-2): 14, 434, 1247, 720, 5
new network - take #2 (LTC)
VshcheIgel6b953e78.standarddiff10.0+0.10LLR: 2.97 (-2.94, 2.94) [0.00, 2.00]
Games: 7616 W: 2087 L: 1790 D: 3739
Ptnml(0-2): 63, 764, 1834, 1107, 40
new network - take #2 (STC)
RosentWinterqnet_402_d32 *diff40.0+0.40LLR: 2.95 (-2.94, 2.94) [0.00, 5.00]
Games: 4092 W: 872 L: 744 D: 2476
Ptnml(0-2): 39, 381, 1085, 495, 46
d32 net update.
VshcheIgelnn-epoch459diff10.0+0.10LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 18594 W: 4884 L: 4574 D: 9136
Ptnml(0-2): 133, 2101, 4487, 2475, 101
new network - take #1 (STC)
JhonnoBerserk[Stockfish] a8a4911bf7ff48b607994b3640faaee8fe406113diffN=5000 *Generated 16668808/16666667 Games
Elo: -20.28 +- 0.15 (95%) [N=16666667]
Games: 16668808 W: 6338235 L: 7309915 D: 3020658
JhonnoBerserk[Stockfish] devdiffN=5000 *Generated 16667560/16666667 Games
Elo: -20.25 +- 0.15 (95%) [N=16666667]
Games: 16667560 W: 6338789 L: 7309198 D: 3019573
VshcheIgelstatic_tt_evaldiff60.0+0.60LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 56366 W: 13159 L: 12823 D: 30384
Ptnml(0-2): 62, 6564, 14583, 6924, 50
3.7.4: store static evaluation in TT
JhonnoBerserk[Stockfish] devdiffN=5000 *Generated 16666676/16666667 Games
Elo: -20.25 +- 0.15 (95%) [N=16666667]
Games: 16666676 W: 6340677 L: 7310748 D: 3015251
RosentWinterqnet_382_d32 *diff8.0+0.08LLR: 2.97 (-2.94, 2.94) [0.00, 5.00]
Games: 17098 W: 4326 L: 4111 D: 8661
Ptnml(0-2): 375, 2021, 3560, 2200, 393
Even larger quantized net. Might not yet be sufficiently mature.
RosentWinterqnet_382_d24 *diff40.0+0.40LLR: 2.95 (-2.94, 2.94) [0.00, 5.00]
Games: 3404 W: 749 L: 622 D: 2033
Ptnml(0-2): 28, 331, 873, 426, 44
Now that net is quantized, we try the larger size again.
RosentWinterqnet_382_d24 *diff8.0+0.08LLR: 2.96 (-2.94, 2.94) [0.00, 5.00]
Games: 12870 W: 3262 L: 3070 D: 6538
Ptnml(0-2): 265, 1499, 2728, 1665, 278
Now that net is quantized, we try the larger size again.
RosentWinterquantize_net *diff40.0+0.40LLR: 2.96 (-2.94, 2.94) [0.00, 5.00]
Games: 1382 W: 324 L: 201 D: 857
Ptnml(0-2): 7, 121, 325, 218, 20
Quantized network. Should be faster, at the cost of a little accuracy.