Multi-objective Reinforcement Learning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
0.93Normalized Hypervolume
41
Mar 27, 2026
0.97Normalized Hypervolume
40
Mar 27, 2026
0.011Multiplicative Gap (ε)
12
Apr 7, 2026
223.55Mean Episode Reward (MER)
11
Mar 25, 2026
1.6MER
11
Mar 25, 2026
22,845.4Hypervolume (HV)
10
Apr 28, 2026
0.239Hypervolume
9
May 14, 2026
294Sparsity
8
Feb 26, 2026
62.5Sparsity
8
Feb 26, 2026
15.4Sparsity
8
Feb 26, 2026
354Sparsity
8
Feb 26, 2026
12.6Sparsity
8
Feb 26, 2026
3.24Sparsity
8
Feb 26, 2026
3.45Sparsity
8
Feb 26, 2026
90.4Sparsity
8
Feb 26, 2026
14.8Sparsity
8
Feb 26, 2026
2.21Sparsity
8
Feb 26, 2026
40.2Sparsity
8
Feb 26, 2026
326Sparsity
8
Feb 26, 2026
521Sparsity
8
Feb 26, 2026
809Sparsity
8
Feb 26, 2026
22Sparsity
8
Feb 26, 2026
20.1Sparsity
8
Feb 26, 2026
1.24Hypervolume (HV)
8
Jun 1, 2026
7.2ESR
7
Jul 1, 2026