List your company

Reinforcement Learning on Atari 2600 (train)

4,314.7ALIEN ScoreDDQL
1,710.8522,386.8513,062.853,738.849Jun 30, 2025

Evaluation results

MethodLinks
DDQLAggregation=Mean of last 3 evaluations during training2025.064,314.7922.11,870.422,896.31,221.9782,803.3964.328,890.65,110.9664.446.195.8234.24,9935,620.7122,65011,725.410,496.3-5.62,04437.933.85,520.619,253.277618,281.5-4.4934.66,560.88,38127,777.203,834.27,618.714,372.1-40.119.8100.414,26914,953.256,757.963.819,617.2-17,661.6805.75,609.259,591.5022.610,314.718315,3491,160.2360,292.76,142.269,460.911,636.4
Double DQNAggregation=Mean of last 3 evaluations during training2025.062,805.1508.91,888.313,371.61,172.4788,923.31,047.521,036.83,988.6579.21.193.6163.44,942.22,204.7110,893.97,330.39,060.2-9.51,820.826.917.95,889.514,134.31,326.127,155.9-6.1626.25,0408,324.526,818.102,728.35,810.16,245.6-37.810.8-137.113,104.113,160.252,21661.56,414.8-19,531.8579.73,544.453,216.3-5.311.19,128.9184.311,864.2628.5222,658.84,204.463,051.57,344.5
DN-DDQLAggregation=Mean of last 3 evaluations during training2025.061,811366.62,462.527,554.41,071.7852,533.31,242.728,458.96,084555.531.197.53071,875.24,152.3115,661.233,47199,210.5-8.22,133.739.732.13,341.626,542.964113,595.8-4569.25,106.69,190.525,96604,215.814,972.45,084.8-1.718.410010,806.111,85953,529.3619,692.6-29,432.1306.47,59371,549.3-3.6-3.510,932.3176.123,914.90185,664.26,671.748,15910,771.2