Multi-objective Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
51.23Hypervolume (HV)
5
Mar 23, 2026
5.743Hypervolume (HV)
5
Mar 23, 2026
100Normalised Hypervolume (HV)
4
Jun 23, 2026
0.542Normalised Hypervolume (HV)
4
Jun 23, 2026
5.02Hypervolume (HV)
4
Jun 1, 2026
3.889Hypervolume (HV)
4
Mar 23, 2026
7.39Hypervolume (HV)
4
Feb 26, 2026
2,500,000Environment Steps
3
Jun 1, 2026
0.428Hypervolume (HV)
3
May 12, 2026
1.168Hypervolume (HV)
3
May 12, 2026
1.33Hypervolume (HV)
3
May 12, 2026
0.299Hypervolume
3
Mar 9, 2026
0.731Hypervolume
3
Mar 9, 2026
0.46Hypervolume
3
Mar 9, 2026
4,310,000Hypervolume
3
Mar 4, 2026
14,600,000Hypervolume
3
Mar 4, 2026
12,100Hypervolume (HV)
3
Feb 26, 2026
15,800,000Hypervolume (x10^7)
3
Feb 26, 2026
3.57Hypervolume (HV)
3
Feb 26, 2026
0.7Hypervolume
2
Mar 9, 2026
0.7Hypervolume
2
Mar 9, 2026
11.08Hypervolume
2
Mar 9, 2026
2Sample Complexity Bound
1
Jun 25, 2026