Reinforcement Learning on Atari 2600 (train)
4,314.7ALIEN ScoreDDQL
Evaluation Results
| Method | Links | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DDQLAggregation=Mean of last 3 evaluations during training2025.06 | 4,314.7 | 922.1 | 1,870.4 | 22,896.3 | 1,221.9 | 782,803.3 | 964.3 | 28,890.6 | 5,110.9 | 664.4 | 46.1 | 95.8 | 234.2 | 4,993 | 5,620.7 | 122,650 | 11,725.4 | 10,496.3 | -5.6 | 2,044 | 37.9 | 33.8 | 5,520.6 | 19,253.2 | 776 | 18,281.5 | -4.4 | 934.6 | 6,560.8 | 8,381 | 27,777.2 | 0 | 3,834.2 | 7,618.7 | 14,372.1 | -40.1 | 19.8 | 100.4 | 14,269 | 14,953.2 | 56,757.9 | 63.8 | 19,617.2 | -17,661.6 | 805.7 | 5,609.2 | 59,591.5 | 0 | 22.6 | 10,314.7 | 183 | 15,349 | 1,160.2 | 360,292.7 | 6,142.2 | 69,460.9 | 11,636.4 | |
| Double DQNAggregation=Mean of last 3 evaluations during training2025.06 | 2,805.1 | 508.9 | 1,888.3 | 13,371.6 | 1,172.4 | 788,923.3 | 1,047.5 | 21,036.8 | 3,988.6 | 579.2 | 1.1 | 93.6 | 163.4 | 4,942.2 | 2,204.7 | 110,893.9 | 7,330.3 | 9,060.2 | -9.5 | 1,820.8 | 26.9 | 17.9 | 5,889.5 | 14,134.3 | 1,326.1 | 27,155.9 | -6.1 | 626.2 | 5,040 | 8,324.5 | 26,818.1 | 0 | 2,728.3 | 5,810.1 | 6,245.6 | -37.8 | 10.8 | -137.1 | 13,104.1 | 13,160.2 | 52,216 | 61.5 | 6,414.8 | -19,531.8 | 579.7 | 3,544.4 | 53,216.3 | -5.3 | 11.1 | 9,128.9 | 184.3 | 11,864.2 | 628.5 | 222,658.8 | 4,204.4 | 63,051.5 | 7,344.5 | |
| DN-DDQLAggregation=Mean of last 3 evaluations during training2025.06 | 1,811 | 366.6 | 2,462.5 | 27,554.4 | 1,071.7 | 852,533.3 | 1,242.7 | 28,458.9 | 6,084 | 555.5 | 31.1 | 97.5 | 307 | 1,875.2 | 4,152.3 | 115,661.2 | 33,471 | 99,210.5 | -8.2 | 2,133.7 | 39.7 | 32.1 | 3,341.6 | 26,542.9 | 641 | 13,595.8 | -4 | 569.2 | 5,106.6 | 9,190.5 | 25,966 | 0 | 4,215.8 | 14,972.4 | 5,084.8 | -1.7 | 18.4 | 100 | 10,806.1 | 11,859 | 53,529.3 | 61 | 9,692.6 | -29,432.1 | 306.4 | 7,593 | 71,549.3 | -3.6 | -3.5 | 10,932.3 | 176.1 | 23,914.9 | 0 | 185,664.2 | 6,671.7 | 48,159 | 10,771.2 |