Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
1Average AUC (z-scored)
13
Jun 16, 2026
98Average AUC (z-scored)
13
Jun 16, 2026
1.43Average AUC (Z-scored)
13
Jun 16, 2026
1.29Avg AUC (z-scored)
13
Jun 16, 2026
1.77Avg AUC (z-scored)
13
Jun 16, 2026
2.18Average AUC (z-scored)
13
Jun 16, 2026
2.39Average AUC (z-scored)
13
Jun 16, 2026
94AL Score
13
Jun 16, 2026
944.5Top Left Score
13
Jun 2, 2026
589.9Run Score
13
Jun 2, 2026
961.5Walk Score
13
Jun 2, 2026
338.8Run Score
13
Jun 2, 2026
1.4Training Time (min)
13
May 29, 2026
0.8Training Time (min)
13
May 29, 2026
1.9Training Time (min)
13
May 29, 2026
0.1Wall-clock Training Time (min)
13
May 29, 2026
5,715Reward
13
Jun 24, 2026
500Max Return
13
Jun 24, 2026
216,793Cumulative Reward
13
Mar 9, 2026
4.815Relative Score
13
Feb 26, 2026
0.024Hopper/Hop Error
13
Feb 26, 2026
22HWRB
13
Feb 26, 2026
103.45Avg Normalized Score
13
May 15, 2026
6,439Avg Reward
13
Feb 26, 2026
106Retention (Task 1)
12
May 27, 2026