FuryBench

Finished
Vine Fury	spsa_final	diff	80.0+0.80	ELO 17.64 +- 7.29 (95%) LLR 2.91 (-2.25, 2.89) [0.00, 5.00] GAMES N: 2168 W: 454 L: 344 D: 1370 PENTA [8, 184, 591, 292, 9]
Vine Fury	spsa_final	diff	40.0+0.40	ELO 44.27 +- 11.79 (95%) LLR 2.94 (-2.25, 2.89) [0.00, 5.00] GAMES N: 860 W: 220 L: 111 D: 529 PENTA [0, 59, 209, 156, 6]
Vine Fury	spsa_final	diff	10.0+0.10	ELO 68.67 +- 15.07 (95%) LLR 2.89 (-2.25, 2.89) [0.00, 5.00] GAMES N: 656 W: 220 L: 92 D: 344 PENTA [0, 37, 145, 127, 19]
Vine Fury	spsa	diff	10.0+0.10	TUNE 10 parameters ITER 6,264 / 6,250 GAMES 50,114 / 50,000
Vine Fury	spsa_1.8k	diff	10.0+0.10	ELO 40.65 +- 11.80 (95%) LLR 2.99 (-2.25, 2.89) [0.00, 5.00] GAMES N: 1142 W: 326 L: 193 D: 623 PENTA [10, 89, 248, 206, 18]
Vine Fury	spsa	diff	10.0+0.10	TUNE 10 parameters ITER 22 / 6,250 GAMES 180 / 50,000
Vine Fury	spsa	diff	10.0+0.10	TUNE 10 parameters ITER 0 / 6,250 GAMES 0 / 50,000
Vine Fury	spsa	diff	40.0+0.40	TUNE 9 parameters ITER 2 / 25,000 GAMES 34 / 400,000
Integral Fury	vine_less_kld	diff	40.0+0.40	ELO -25.86 +- 6.38 (95%) GAMES N: 3002/3000 W: 584 L: 807 D: 1611 PENTA [0, 500, 742, 241, 18]
Integral Fury	less_kld	diff	40.0+0.40	ELO -9.05 +- 4.47 (95%) LLR -2.27 (-2.25, 2.89) [0.00, 2.50] GAMES N: 5566 W: 1323 L: 1468 D: 2775 PENTA [3, 727, 1470, 578, 5]
Integral Fury	less_kld	diff	10.0+0.10	ELO -6.63 +- 4.00 (95%) LLR -2.28 (-2.25, 2.89) [0.00, 2.50] GAMES N: 7858 W: 1923 L: 2073 D: 3862 PENTA [32, 1025, 1952, 901, 19]
Vine Fury	dual_act	diff	40.0+0.40	ELO -0.10 +- 2.55 (95%) LLR -2.28 (-2.25, 2.89) [0.00, 5.00] GAMES N: 20430 W: 4077 L: 4083 D: 12270 PENTA [124, 2432, 5108, 2428, 123]
Integral Fury	[Vine] datagen_conditions	time odds diff	N=5000	ELO 154.28 +- 9.67 (95%) GAMES N: 3072/3000 W: 1687 L: 406 D: 979 PENTA [20, 90, 392, 657, 377]
Vine Fury	datagen_conditions	diff	10.0+0.10	ELO 63.71 +- 8.18 (95%) GAMES N: 3000/3000 W: 1136 L: 592 D: 1272 PENTA [30, 204, 592, 540, 134]
Vine Fury	datagen_conditions	diff	N=100000	ELO -1.36 +- 12.33 (95%) GAMES N: 1024/3000 W: 298 L: 302 D: 424 PENTA [21, 93, 284, 97, 17]
Integral Fury	[Vine] datagen_conditions	time odds diff	N=20000	ELO 314.83 +- 14.80 (95%) GAMES N: 1660/3000 W: 1221 L: 27 D: 412 PENTA [0, 1, 37, 389, 403]
Integral Fury	[Vine] datagen_conditions	time odds diff	N=20000	ELO 336.49 +- 11.74 (95%) GAMES N: 3072/3000 W: 2337 L: 39 D: 696 PENTA [0, 3, 57, 651, 825]
Vine Fury	datagen_conditions	diff	N=100000	ELO 65.07 +- 7.79 (95%) GAMES N: 3376/3000 W: 1269 L: 644 D: 1463 PENTA [34, 221, 688, 576, 169]
Vine Fury	datagen_conditions	diff	N=100000	ELO 135.71 +- 8.62 (95%) GAMES N: 3614/10000 W: 1850 L: 506 D: 1258 PENTA [13, 149, 527, 717, 401]
Vine Fury	datagen_conditions	diff	N=100000	ELO -0.00 +- 0.00 (95%) LLR -0.21 (-2.25, 2.89) [0.00, 5.00] GAMES N: 1024 W: 220 L: 220 D: 584 PENTA [0, 0, 512, 0, 0]
Vine Fury	datagen_conditions	diff	N=100000	ELO 0.00 +- 0.00 (95%) LLR 0.00 (-2.25, 2.89) [0.00, 5.00] GAMES N: 0 W: 0 L: 0 D: 0 PENTA [0, 0, 0, 0, 0]
Vine Fury	policy_4096hl	diff	10.0+0.10	ELO -54.92 +- 15.58 (95%) LLR -2.64 (-2.25, 2.89) [0.00, 5.00] GAMES N: 708 W: 119 L: 230 D: 359 PENTA [23, 124, 150, 55, 2]
Integral Fury	no_tree_reuse	diff	40.0+0.40	ELO -21.28 +- 9.76 (95%) LLR -2.26 (-2.25, 2.89) [0.00, 5.00] GAMES N: 1226 W: 260 L: 335 D: 631 PENTA [1, 190, 306, 115, 1]
Integral Fury	no_tree_reuse	diff	10.0+0.10	ELO -8.51 +- 4.51 (95%) LLR -2.25 (-2.25, 2.89) [0.00, 2.50] GAMES N: 6206 W: 1504 L: 1656 D: 3046 PENTA [30, 814, 1556, 684, 19]
Integral Fury	vine_vondele	diff	10.0+0.10	ELO -4.24 +- 3.27 (95%) LLR -2.25 (-2.25, 2.89) [0.00, 2.50] GAMES N: 11462 W: 2801 L: 2941 D: 5720 PENTA [38, 1438, 2917, 1302, 36]

1 2 3 7 8 9 10 11 33 34 35

FuryBench Testing Framework