Reinforcement Learning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
36,783,880.67AUC@T
2
Feb 27, 2026
-25,766,227.01AUC @ T
2
Feb 27, 2026
42,642,395.61AUC@T
2
Feb 27, 2026
42,687,915.83AUC@T
2
Feb 27, 2026
32,301,685.83AUC@T
2
Feb 27, 2026
9,392,950.11AUC@T
2
Feb 27, 2026
-84,528,355.1AUC@T
2
Feb 27, 2026
-80,111,477.55AUC @ T
2
Feb 27, 2026
-79,144,263.52AUC@T
2
Feb 27, 2026
109.6Normalized Score
2
Feb 26, 2026
110.51D4RL Score
2
Feb 26, 2026
72.36D4RL Score
2
Feb 26, 2026
1.039D4RL Score
2
Feb 26, 2026
80.86D4RL Score
2
Feb 26, 2026
125.47D4RL Score
2
Feb 26, 2026
89.39D4RL Score
2
Feb 26, 2026
75.98D4RL Score
2
Feb 26, 2026
42.16D4RL Score
2
Feb 26, 2026
7,540,000Total Environment Steps
2
Feb 26, 2026
17Length
2
Feb 26, 2026
24.6Episode Length
2
Feb 26, 2026
16.5Episode Length
2
Feb 26, 2026
13Episode Length
2
Feb 26, 2026
15Episode Length
2
Feb 26, 2026
8Episode Length
2
Feb 26, 2026