Multi-objective Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
6.67ESR
7
Jul 1, 2026
3.25Hypervolume (HV)
7
May 12, 2026
5.08UT
7
Apr 28, 2026
0.589Normalised Hypervolume (HV)
6
Jun 23, 2026
74.32Normalised Hypervolume (HV)
6
Jun 23, 2026
10.62Hypervolume (HV)
6
Jun 17, 2026
24.4Hypervolume (HV)
6
Jun 17, 2026
2.91Hypervolume (HV)
6
Jun 17, 2026
9.61Hypervolume (HV)
6
Jun 1, 2026
3.54Hypervolume (HV)
6
Jun 1, 2026
7.04Hypervolume
6
Jun 1, 2026
3.68Hypervolume (HV)
6
Jun 1, 2026
3.51Hypervolume
6
Jun 1, 2026
2.04Hypervolume (HV)
6
Jun 1, 2026
4.25Hypervolume (HV)
6
May 12, 2026
22,500HV (x10^4)
6
Mar 4, 2026
6,520,000Hypervolume (HV)
6
Mar 4, 2026
1Sample Complexity Bound
5
Jun 25, 2026
15.13Normalized Hypervolume (HV)
5
Jun 23, 2026
1.97Hypervolume (HV)
5
Jun 1, 2026
2.09Hypervolume
5
Jun 1, 2026
3.187Hypervolume
5
Mar 23, 2026
6.814Hypervolume (HV)
5
Mar 23, 2026
22.09Hypervolume (HV)
5
Mar 23, 2026
5.787Hypervolume (HV)
5
Mar 23, 2026