ResearchBenchmarksMulti-Objective Reinforcement Learning on resource-gathering v0Follow100Normalised Hypervolume (HV)MERLION6.233630.576854.9279.2632Jun 20, 2026Evaluation ResultsMethodMethodLinksNormalised Hypervolume (HV)Sparsity (Spar)MERLION2026.061000Meta-MORL2026.064032.75MPMOQL2026.0614.2132.72MORL/D2026.069.842.33