Deep Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
74.2Usefulness
4
Apr 21, 2026
12IQM Return
4
Apr 16, 2026
0IQM Return
4
Apr 16, 2026
19.8IQM Return
4
Apr 16, 2026
8,160IQM Return
4
Apr 16, 2026
1,642IQM Return
4
Apr 16, 2026
1,028IQM Return
4
Apr 16, 2026
364IQM Return
4
Apr 16, 2026
0.093Median Human Normalized Score
3
Mar 18, 2026