Reinforcement Learning on Atari 100k (26 Game Scores and Summary Statistics)
7,128Alien ScoreHuman
Evaluation results
| Method | Links | ||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HumanSteps=—2025.02 | 7,128 | 1,720 | 742 | 8,503 | 753 | 37,188 | 12 | 30 | 7,388 | 35,829 | 1,971 | 30 | 4,335 | 2,412 | 30,826 | 303 | 3,035 | 2,666 | 22,736 | 6,952 | 15 | 69,571 | 13,544 | 7,845 | 42,055 | 11,693 | — | — | — | — | — | — | — | — | |
| Human2022.01 | 7,127.7 | 1,719.5 | 742 | 8,503.3 | 753.1 | 37,187.5 | 12.1 | 30.5 | 7,387.8 | 35,829.4 | 1,971 | 29.6 | 4,334.7 | 2,412.5 | 30,826.4 | 302.8 | 3,035 | 2,665.5 | 22,736.3 | 6,951.6 | 14.6 | 69,571.3 | 13,455 | 7,845 | 42,054.7 | 11,693.2 | 1 | 0 | — | — | — | — | — | — | |
| Human2024.05 | 7,127.7 | 1,719.5 | 742 | 8,503.3 | 753.1 | 37,187.5 | 12.1 | 30.5 | 7,387.8 | 35,829.4 | 1,971 | 29.6 | 4,334.7 | 2,412.5 | 30,826.4 | 302.8 | 3,035 | 2,665.5 | 22,736.3 | 6,951.6 | 14.6 | 69,571.3 | 13,455 | 7,845 | 42,054.7 | 11,693.2 | 1 | — | — | 1 | — | — | — | — | |
| Human2025.02 | 7,127.7 | 1,719.5 | 742 | 8,503.3 | 753.1 | 37,187.5 | 12.1 | 30.5 | 7,387.8 | 35,829.4 | 1,971 | 29.6 | 4,334.7 | 2,412.5 | 30,826.4 | 302.8 | 3,035 | 2,665.5 | 22,736.3 | 6,951.6 | 14.6 | 69,571.3 | 13,455 | 7,845 | 42,054.7 | 11,693.2 | 1 | 0 | — | 1 | — | 1 | — | — | |
| Human2026.05 | 7,127.7 | 1,719.5 | 742 | 8,503.3 | 753.1 | 37,187.5 | 12.1 | 30.5 | 7,387.8 | 35,829.4 | 1,971 | 29.6 | 4,334.7 | 2,412.5 | 30,826.4 | 302.8 | 3,035 | 2,665.5 | 22,736.3 | 6,951.6 | 14.6 | 69,571.3 | 13,455 | 7,845 | 42,054.7 | 11,693.2 | 1 | 0 | — | 1 | — | — | — | — | |
| Human2026.07 | 7,127.7 | 1,719.5 | 742 | 8,503.3 | 753.1 | 37,187.5 | 12.1 | 30.5 | 7,387.8 | 35,829.4 | 1,971 | 29.6 | 4,334.7 | 2,412.5 | 30,826.4 | 302.8 | 3,035 | 2,665.5 | 22,736.3 | 6,951.6 | 14.6 | 69,571.3 | 13,455 | 7,845 | 42,054.7 | 11,693.2 | — | — | — | — | — | — | — | — | |
| EvolvingAgentSteps=400K, Evaluation Protocol=Zero-shot generalization2025.02 | 1,392 | 329 | 981 | 1,492 | 362 | 24,830 | 91 | 13 | 4,375 | 78,215 | 1,205 | 5 | 3,674 | 2,219 | 12,168 | 621 | 2,753 | 10,027 | 28,692 | 3,246 | -2 | 5,285 | 4,793 | 21,703 | 2,305 | 37,284 | — | — | — | — | — | — | — | — | |
| CoIT2026.07 | 1,206.7 | 182.3 | 635.7 | 709 | 124.9 | 13,760 | 23.6 | 16.1 | 1,338 | 17,538 | 864.6 | 29.6 | 2,069.8 | 746.8 | 7,572.8 | 336 | 4,116.6 | 3,436.2 | 9,250 | 1,509.6 | 1.5 | 145.7 | 2,117.5 | 11,758.5 | 554 | 4,734.2 | — | — | — | — | — | — | — | — | |
| MPRseeds=10, episodes per seed=1002026.07 | 1,186 | 254.1 | 667.3 | 799.1 | 67.3 | 20,274.8 | 21 | 18.1 | 837.8 | 24,902.36 | 1,176.7 | 29.6 | 2,964 | 558.8 | 11,044.1 | 400.1 | 1,286.3 | 4,724.5 | 17,797.4 | 1,413.8 | -6.9 | 100 | 4,333 | 16,157.8 | 677.2 | 8,630.4 | — | — | — | — | — | — | — | — | |
| DreamerV3Steps=400K, Evaluation Protocol=Zero-shot generalization2025.02 | 1,118 | 97 | 683 | 1,062 | 398 | 20,300 | 82 | 10 | 2,222 | 86,225 | 577 | 0 | 3,377 | 2,160 | 13,354 | 540 | 2,643 | 8,171 | 25,900 | 1,521 | -4 | 3,238 | 2,921 | 19,230 | 962 | 46,910 | — | — | — | — | — | — | — | — | |
| JEDIBatch size=322026.05 | 1,090.1 | 114.3 | 1,394.5 | 2,331 | 926.1 | 16,084 | 91.6 | 155.6 | 1,392.4 | 64,786.2 | 2,047.2 | 6.3 | 263.3 | 4,155.3 | 7,442.9 | 460.5 | 736 | 8,499.4 | 12,725.2 | 1,075.9 | 18.2 | 95.2 | 3,606.1 | 14,690 | 1,103.7 | 4,191.1 | 0.609 | 0.48 | 11 | 1.361 | — | — | — | — | |
| JEDI2026.05 | 1,090.1 | 120.2 | 1,394.5 | 2,626.3 | 926.1 | 16,084 | 91.6 | 155.6 | 1,589.2 | 69,585.8 | 2,047.2 | 6.3 | 263.3 | 4,155.3 | 7,442.9 | 460.5 | 962.8 | 8,676.9 | 21,340.6 | 1,075.9 | 18.4 | 95.2 | 3,606.1 | 25,736.6 | 1,103.7 | 4,271.4 | 0.688 | 0.46 | 11 | 1.45 | — | — | 7 | — | |
| DreamerV32026.05 | 1,078.9 | 141.2 | 669.7 | 946.4 | 622.7 | 12,400 | 73.8 | 27.9 | 411.7 | 84,880 | 433.7 | 0 | 945.1 | 5,754.3 | 11,145.2 | 480.4 | 3,790 | 7,921.5 | 24,210 | 1,358.4 | 18.9 | 1,081.4 | 3,291.3 | 14,995 | 610 | 7,981.7 | 0.504 | 0.5 | 9 | 1.134 | — | — | 0 | — | |
| MLR2022.01 | 990.1 | 227.7 | 643.7 | 883.7 | 180.3 | 16,080 | 26.4 | 16.8 | 910.7 | 24,633.3 | 854.6 | 30.2 | 2,381.1 | 822.3 | 7,919.3 | 423.2 | 8,516 | 3,923.1 | 10,652 | 1,481.3 | 4.9 | 100 | 3,410.4 | 12,049.7 | 628.3 | 6,675.7 | 0.432 | 0.522 | — | — | — | — | — | — | |
| MLR2026.07 | 990.1 | 227.7 | 643.7 | 883.7 | 180.3 | 16,080 | 26.4 | 16.8 | 910.7 | 24,633.3 | 854.6 | 30.2 | 2,381.1 | 822.3 | 7,919.3 | 423.2 | 8,516 | 3,923.1 | 10,652 | 1,481.3 | 4.9 | 100 | 3,410.4 | 12,049.7 | 628.3 | 6,675.7 | — | — | — | — | — | — | — | — | |
| STORM2024.05 | 983.6 | 204.8 | 801 | 1,028 | 641.2 | 13,540 | 79.7 | 15.9 | 1,888 | 66,776 | 164.6 | 33.5 | 1,316 | 8,239.6 | 11,044.3 | 509 | 4,208 | 8,412.6 | 26,182 | 2,673.5 | 11.3 | 7,781 | 4,522.5 | 17,564 | 525.2 | 7,985 | 0.636 | — | 10 | 1.266 | — | — | — | — | |
| STORMNumber of runs=52025.02 | 983.6 | 204.8 | 801 | 1,028 | 641.2 | 13,540 | 79.7 | 15.9 | 1,888 | 66,776 | 164.6 | 0 | 1,316 | 8,239.6 | 11,044.3 | 509 | 4,208 | 8,412.6 | 26,182 | 2,673.5 | 11.3 | 7,781 | 4,522.5 | 17,564 | 525.2 | 7,985 | 0.561 | 0.472 | 9 | 1.222 | — | 0.425 | — | — | |
| TWISTER2026.05 | 970 | 184 | 721 | 1,306 | 942 | 9,920 | 88 | 35 | 910 | 81,880 | 289 | 32 | 305 | 22,234 | 8,773 | 573 | 6,016 | 8,839 | 23,442 | 2,206 | 20 | 1,608 | 3,197 | 17,832 | 532 | 7,068 | — | — | 12 | 1.621 | — | — | 6 | — | |
| DreamerV3Number of runs=52025.02 | 959.4 | 139.1 | 705.6 | 932.5 | 648.7 | 12,250 | 78 | 31.1 | 410 | 97,190 | 303.3 | 0 | 909.4 | 3,730 | 11,160.5 | 444.6 | 4,098.3 | 7,781.5 | 21,420 | 1,326.9 | 18.4 | 881.6 | 3,405.1 | 15,565 | 618 | 7,567.1 | 0.487 | 0.51 | 9 | 1.124 | — | 0.485 | — | — | |
| DreamerV32024.05 | 959 | 139 | 706 | 932 | 649 | 12,250 | 78 | 31 | 420 | 97,190 | 303 | 0 | 909 | 3,730 | 11,161 | 445 | 4,098 | 7,782 | 21,420 | 1,327 | 18 | 882 | 3,405 | 15,565 | 618 | 9,234 | 0.497 | — | 9 | 1.097 | — | — | — | — | |
| PlayVirtual2022.01 | 947.8 | 165.3 | 702.3 | 933.3 | 245.9 | 13,260 | 38.3 | 20.6 | 922.4 | 23,176.7 | 1,131.7 | 16.1 | 1,984.7 | 684.3 | 8,597.5 | 394.7 | 2,384.7 | 3,880.7 | 14,259 | 1,335.4 | -3 | 86 | 3,620.1 | 13,429.4 | 532.9 | 10,225.2 | 0.374 | 0.558 | — | — | — | — | — | — | |
| SPR2022.01 | 841.9 | 179.7 | 565.6 | 962.5 | 345.4 | 14,834.1 | 35.7 | 19.6 | 946.3 | 36,700.5 | 517.6 | 19.3 | 1,170.7 | 660.6 | 5,858.6 | 366.5 | 3,617.4 | 3,681.6 | 14,783.2 | 1,318.4 | -5.4 | 24.8 | 866.3 | 12,213.1 | 558.1 | 10,859.2 | 0.337 | 0.577 | — | — | — | — | — | — | |
| DER2022.01 | 802.3 | 125.9 | 561.5 | 535.4 | 185.5 | 8,977 | -0.3 | 9.2 | 925.9 | 34,508.6 | 627.6 | 20.9 | 871 | 467 | 6,226 | 275.7 | 581.7 | 3,256.9 | 6,580.1 | 1,187.4 | -9.7 | 11.5 | 1,773.5 | 2,606.4 | 304.6 | 3,075 | 0.183 | 0.698 | — | — | — | — | — | — | |
| JEDIBatch size=642026.05 | 801.6 | 120.2 | 1,388.3 | 2,626.3 | 653.3 | 9,056 | 86.8 | 128.3 | 1,589.2 | 69,585.8 | 1,933.6 | 0 | 263.3 | 4,010.6 | 6,861.1 | 448.2 | 962.8 | 8,676.9 | 21,340.6 | 1,024.4 | 18.4 | 90.5 | 3,447.1 | 25,736.6 | 989.6 | 4,271.4 | 0.618 | 0.488 | 9 | 1.358 | — | — | — | — | |
| SPR2026.07 | 801.5 | 176.3 | 571 | 977.8 | 380.9 | 16,651 | 35.8 | 17.1 | 974.8 | 42,923.6 | 545.2 | 24.4 | 1,821.5 | 715.2 | 7,019.2 | 349 | 3,276.4 | 3,688.9 | 13,192.7 | 1,313.2 | -5.9 | 124 | 669.1 | 14,220.5 | 583.1 | 28,138.5 | — | — | — | — | — | — | — | — | |
| DrQ2026.07 | 771.2 | 102.8 | 452.4 | 603.5 | 168.9 | 12,954 | 6 | 16.1 | 780.3 | 20,516.5 | 1,113.4 | 9.8 | 331.1 | 636.3 | 3,736.3 | 236 | 940.6 | 4,018.1 | 9,111 | 960.5 | -8.5 | -13.6 | 854.4 | 8,895.1 | 301.2 | 3,180.8 | — | — | — | — | — | — | — | — | |
| STORM2026.05 | 748.2 | 144 | 1,376.7 | 1,318.5 | 990 | 5,830 | 81.2 | 41 | 1,644 | 79,196 | 324.6 | 0 | 365.9 | 5,307.2 | 11,434.1 | 408 | 3,512 | 6,522.2 | 20,046 | 1,489.5 | 18.4 | 100 | 2,910.5 | 14,841 | 557.4 | 6,127.9 | 0.557 | 0.489 | 11 | 1.142 | — | — | 2 | — | |
| DIAMOND2024.05 | 744.1 | 225.8 | 1,526.4 | 3,698.5 | 19.7 | 4,702 | 86.9 | 132.5 | 1,369.8 | 99,167.8 | 288.1 | 33.3 | 274.1 | 5,897.9 | 5,621.8 | 427.4 | 5,382.2 | 8,610.1 | 18,713.6 | 1,958.2 | 20.4 | 114.3 | 4,499.3 | 20,673.2 | 551.2 | 3,856.3 | 0.641 | — | 11 | 1.459 | — | — | — | — | |
| DIAMONDNumber of runs=52025.02 | 744.1 | 225.8 | 1,526.4 | 3,698.5 | 19.7 | 4,702 | 86.9 | 132.5 | 1,369.8 | 99,167.8 | 288.1 | 33.3 | 274.1 | 5,897.9 | 5,621.8 | 427.4 | 5,382.2 | 8,610.1 | 18,713.6 | 1,958.2 | 20.4 | 114.3 | 4,499.3 | 20,673.2 | 551.2 | 3,856.3 | 0.641 | 0.48 | 11 | 1.459 | — | 0.373 | — | — | |
| DIAMOND2026.05 | 744.1 | 225.8 | 1,526.4 | 3,698.5 | 19.7 | 4,702 | 86.9 | 132.5 | 1,369.8 | 99,167.8 | 288.1 | 33.3 | 274.1 | 5,897.9 | 5,621.8 | 427.4 | 5,382.2 | 8,610.1 | 18,713.6 | 1,958.2 | 20.4 | 114.3 | 4,499.3 | 20,673.2 | 551.2 | 3,856.3 | 0.641 | 0.48 | 11 | 1.459 | — | — | 7 | — | |
| DrQ2022.01 | 734.1 | 94.2 | 479.5 | 535.6 | 153.4 | 10,563.6 | 6.6 | 15.4 | 792.4 | 21,991.6 | 1,142.4 | 17.8 | 508.1 | 618 | 3,722.6 | 251.8 | 974.5 | 4,131.4 | 7,154.5 | 1,002.9 | -14.3 | 81.9 | 934.2 | 12,023.1 | 310.5 | 3,619.1 | 0.224 | 0.692 | — | — | — | — | — | — | |
| CURL2022.01 | 711 | 113.7 | 500.9 | 567.2 | 65.3 | 8,997.8 | 0.9 | 2.6 | 783.5 | 9,154.4 | 646.5 | 28.3 | 1,226.5 | 400.9 | 4,987.7 | 331 | 740.2 | 3,049.2 | 8,155.6 | 1,064 | -18.5 | 59.6 | 727 | 8,036.1 | 315.2 | 2,646.4 | 0.113 | 0.768 | — | — | — | — | — | — | |
| SIMULUSNumber of runs=52025.02 | 687.2 | 102.4 | 1,822.8 | 1,369.1 | 347.1 | 13,262 | 93.5 | 148.9 | 3,611.6 | 93,433.2 | 4,787.6 | 31.9 | 258.4 | 4,363.2 | 7,466.8 | 678 | 6,656 | 6,677.3 | 31,705.4 | 1,282.7 | 19.9 | 100 | 2,425.6 | 24,471.8 | 1,800.4 | 10,416.5 | 0.99 | 0.412 | 13 | 1.645 | — | 0.982 | — | — | |
| Baseline2022.01 | 678.5 | 132.8 | 493.3 | 1,021.3 | 288.2 | 13,076.7 | 14.3 | 16.7 | 878.7 | 28,235.7 | 310.5 | 30.9 | 994.3 | 650.9 | 4,661.2 | 270 | 5,036 | 3,571.3 | 10,517.3 | 1,320.9 | -3.1 | 93.3 | 553.8 | 12,337 | 471.9 | 4,112.8 | 0.292 | 0.614 | — | — | — | — | — | — | |
| TWM2024.05 | 674.6 | 121.8 | 682.6 | 1,116.6 | 466.7 | 5,068 | 77.5 | 20 | 1,697.4 | 71,820.4 | 350.2 | 24.3 | 1,475.6 | 1,674.8 | 7,254 | 362.4 | 1,240 | 6,349.2 | 24,554.6 | 1,588.4 | 18.8 | 86.6 | 3,330.8 | 9,109 | 774.4 | 15,981.7 | 0.459 | — | 8 | 0.956 | — | — | — | — | |
| TWMNumber of runs=52025.02 | 674.6 | 121.8 | 682.6 | 1,116.6 | 466.7 | 5,068 | 77.5 | 20 | 1,697.4 | 71,820.4 | 350.2 | 24.3 | 1,475.6 | 1,674.8 | 7,254 | 362.4 | 1,240 | 6,349.2 | 24,554.6 | 1,588.4 | 18.8 | 86.6 | 3,330.8 | 9,109 | 774.4 | 15,981.7 | 0.459 | 0.513 | 8 | 0.956 | — | 0.505 | — | — | |
| TWM2026.05 | 674.6 | 121.8 | 682.6 | 1,116.6 | 466.7 | 5,068 | 77.5 | 20 | 1,697.4 | 71,820.4 | 350.2 | 24.3 | 1,475.6 | 1,674.8 | 7,254 | 362.4 | 1,240 | 6,349.2 | 24,554.6 | 1,588.4 | 18.8 | 86.6 | 3,330.8 | 9,109 | 774.4 | 15,981.7 | 0.459 | 0.513 | 8 | 0.956 | — | — | 4 | — | |
| SimPLe2024.05 | 616.9 | 74.3 | 527.2 | 1,128.3 | 34.2 | 4,031.2 | 7.8 | 16.4 | 979.4 | 62,583.6 | 208.1 | 16.7 | 236.9 | 596.8 | 2,656.6 | 100.5 | 51.2 | 2,204.8 | 14,862.5 | 1,480 | 12.8 | 35 | 1,288.8 | 5,640.6 | 683.3 | 3,350.3 | 0.13 | — | 1 | 0.332 | — | — | — | — | |
| SimPLe2026.07 | 616.9 | 88 | 527.2 | 1,128.3 | 34.2 | 5,184.4 | 9.1 | 16.4 | 1,246.9 | 62,583.6 | 208.1 | 20.3 | 254.7 | 771 | 2,656.6 | 125.3 | 323.1 | 4,539.9 | 17,257.2 | 1,480 | 12.8 | 58.3 | 1,288.8 | 5,640.6 | 683.3 | 3,350.3 | — | — | — | — | — | — | — | — | |
| REMNumber of runs=52025.02 | 607.2 | 95.3 | 1,764.2 | 1,637.5 | 19.2 | 11,826 | 87.5 | 90.7 | 2,561.2 | 76,547.6 | 5,738.6 | 32.3 | 240.5 | 5,452.4 | 6,484.8 | 391.2 | 467.6 | 4,017.7 | 25,172.2 | 962.5 | 18 | 99.6 | 743 | 14,060.2 | 1,036.7 | 3,757.6 | 0.673 | 0.482 | 12 | 1.222 | — | 0.28 | — | — | |
| OTR2022.01 | 570.8 | 77.7 | 330.9 | 334.7 | 55 | 5,139.4 | 1.6 | 8.1 | 813.3 | 14,999.3 | 681.6 | 11.5 | 224.9 | 539.4 | 5,956.5 | 88 | 348.5 | 3,655.9 | 6,659.6 | 908 | -2.5 | 72.8 | 552.5 | 272.9 | 272.9 | 2,831 | 0.117 | 0.819 | — | — | — | — | — | — | |
| CURL2026.07 | 558.2 | 142.1 | 600.6 | 734.5 | 131.6 | 14,870 | 1.2 | 4.9 | 1,058.5 | 12,146.5 | 817.6 | 26.7 | 1,181.3 | 669.3 | 6,279.3 | 471 | 872.5 | 4,229.6 | 14,307.8 | 1,465.5 | -16.5 | 218.4 | 1,042.4 | 5,661 | 384.5 | 2,955.2 | — | — | — | — | — | — | — | — | |
| IRIS2024.05 | 420 | 143 | 1,524.4 | 853.6 | 53.1 | 13,074 | 70.1 | 83.7 | 1,565 | 59,324.2 | 2,034.4 | 31.1 | 259.1 | 2,236.1 | 7,037.4 | 462.7 | 838.2 | 6,616.4 | 21,759.8 | 999.1 | 14.6 | 100 | 745.7 | 9,614.6 | 661.3 | 3,546.2 | 0.501 | — | 10 | 1.046 | — | — | — | — | |
| IRIS2026.05 | 420 | 143 | 1,524.4 | 853.6 | 53.1 | 13,074 | 70.1 | 83.7 | 1,565 | 59,324.2 | 2,034.4 | 31.1 | 259.1 | 2,236.1 | 7,037.4 | 462.7 | 838.2 | 6,616.4 | 21,759.8 | 999.1 | 14.6 | 100 | 745.7 | 9,614.6 | 661.3 | 3,546.2 | 0.501 | 0.512 | 10 | 1.046 | — | — | 0 | — | |
| PPOSteps=400K, Evaluation Protocol=Zero-shot generalization2025.02 | 276 | 26 | 327 | 292 | 14 | 2,233 | 3 | 3 | 1,005 | 14,675 | 160 | 2 | 127 | 368 | 2,596 | 41 | 55 | 3,222 | 2,090 | 366 | -20 | 100 | 317 | 602 | 305 | 1,502 | — | — | — | — | — | — | — | — | |
| Random2022.01 | 227.8 | 5.8 | 222.4 | 210 | 14.2 | 2,360 | 0.1 | 1.7 | 811 | 10,780.5 | 152.1 | 0 | 65.2 | 257.6 | 1,027 | 29 | 52 | 1,598 | 258.5 | 307.3 | -20.7 | 24.9 | 163.9 | 68.4 | 63.4 | 533.4 | 0 | 1 | — | — | — | — | — | — | |
| Random2024.05 | 227.8 | 5.8 | 222.4 | 210 | 14.2 | 2,360 | 0.1 | 1.7 | 811 | 10,780.5 | 152.1 | 0 | 65.2 | 257.6 | 1,027 | 29 | 52 | 1,598 | 258.5 | 307.3 | -20.7 | 24.9 | 163.9 | 11.5 | 68.4 | 533.4 | 0 | — | 0 | 0 | — | — | — | — | |
| Random2025.02 | 227.8 | 5.8 | 222.4 | 210 | 14.2 | 2,360 | 0.1 | 1.7 | 811 | 10,780.5 | 152.1 | 0 | 65.2 | 257.6 | 1,027 | 29 | 52 | 1,598 | 258.5 | 307.3 | -20.7 | 24.9 | 163.9 | 11.5 | 68.4 | 533.4 | 0 | 1 | 0 | 0 | — | 0 | — | — | |
| Random2026.05 | 227.8 | 5.8 | 222.4 | 210 | 14.2 | 2,360 | 0.1 | 1.7 | 811 | 10,780.5 | 152.1 | 0 | 65.2 | 257.6 | 1,027 | 29 | 52 | 1,598 | 258.5 | 307.3 | -20.7 | 24.9 | 163.9 | 11.5 | 68.4 | 533.4 | 0 | 1 | 0 | 0 | — | — | 0 | — | |
| Random2026.07 | 227.8 | 5.8 | 222.4 | 210 | 14.2 | 2,360 | 0.1 | 1.7 | 811 | 10,780.5 | 152.1 | 0 | 65.2 | 257.6 | 1,027 | 29 | 52 | 1,598 | 258.5 | 307.3 | -20.7 | 24.9 | 163.9 | 11.5 | 68.4 | 533.4 | — | — | — | — | — | — | — | — | |
| Diamondenvironment interactions=100K, evaluation episodes=1002026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.641 | 0.48 | — | — | — | — | — | — | |
| DIAMOND2025.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.46 | 2.08 | — | — | — | |
| DreamerV32025.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.13 | 1.81 | — | — | — | |
| DreamerV3environment interactions=100K, evaluation episodes=1002026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.487 | 0.51 | — | — | — | — | — | — | |
| DreamerV32026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.54 | — | — | — | — | 0.49 | — | 1.25 | |
| IRIS2025.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.05 | 1.53 | — | — | — | |
| ITCenvironment interactions=100K, evaluation episodes=100, backbone=Simulus, seeds=52026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.092 | 0.376 | — | — | — | — | — | — | |
| JEDI2025.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.36 | 2.04 | — | — | — | |
| MR.Q2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.41 | — | — | — | — | 0.4 | — | 0.91 | |
| NASDAQ2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.42 | — | — | — | — | 0.34 | — | 0.93 | |
| Rainbowvariant=enhanced2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.35 | — | — | — | — | 0.29 | — | 0.54 | |
| ScaleZeroLearning Protocol=MT2025.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.39 | — | 0.16 | — | — | |
| Simulusenvironment interactions=100K, evaluation episodes=1002026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.99 | 0.412 | — | — | — | — | — | — | |
| SPR2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.43 | — | — | — | — | 0.42 | — | 0.65 | |
| STORM2025.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1.22 | 1.83 | — | — | — | |
| STORMenvironment interactions=100K, evaluation episodes=1002026.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.561 | 0.472 | — | — | — | — | — | — | |
| TWM2025.05 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.956 | 1.55 | — | — | — | |
| UniZeroLearning Protocol=ST2025.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.38 | — | 0.21 | — | — | |
| UniZeroLearning Protocol=MT2025.09 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.31 | — | 0.16 | — | — |