Policy Optimization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
109.86Mean (± Std)
156
May 15, 2026
4,150Avg Training Steps
18
Feb 26, 2026
3.65True Performance
8
Apr 15, 2026
16.91True Outcome
8
Apr 15, 2026
-7Sample Complexity
8
Mar 17, 2026
5,806Average Training Steps
7
Feb 26, 2026
3,767Average Training Steps
7
Feb 26, 2026
5,630Average Training Steps
7
Feb 26, 2026
3,125Average Training Steps
7
Feb 26, 2026
5,630Average Training Steps
7
Feb 26, 2026
3,125Avg Training Steps
7
Feb 26, 2026
6.3True Outcome
6
Apr 15, 2026
0.063Gini Index
6
Feb 26, 2026
0.019Gini Index
6
Feb 26, 2026
8.3True Score
5
Apr 15, 2026
100Average Normalized Performance
5
Feb 26, 2026
49.1Return
5
Feb 26, 2026
13.3Return
5
Feb 26, 2026
2.8Return
5
Feb 26, 2026
221.1Return
5
Feb 26, 2026
60.7Return
5
Feb 26, 2026
71Return
5
Feb 26, 2026
0Preprocessing Time
1
Feb 26, 2026
—
—Primary metric
0
Jun 2, 2026
—
—Primary metric
0
Feb 26, 2026