ResearchBenchmarksMulti-Objective Reinforcement Learning on MO-Hopper Hopper-2obj v5Multi-Objective Reinforcement Learning on MO-Hopper Hopper-2obj v5Follow4,310,000HypervolumeMORL/D3,124,4003,432,2003,740,0004,047,800Mar 3, 2026Evaluation resultsMethodMethodLinksHypervolumeSparsityMORL/D2026.034,310,000115.5MAPEX2026.033,340,000209.6MOPDERL2026.033,170,00064.2