ResearchBenchmarksMulti-Objective Reinforcement Learning on mo-reacher v4Multi-Objective Reinforcement Learning on mo-reacher v4Follow15.13Normalized Hypervolume (HV)Meta-MORL-0.56363.51077.58511.6593Jun 20, 2026Evaluation resultsMethodMethodLinksNormalized Hypervolume (HV)SparsityMeta-MORL2026.0615.1318.83MERLION2026.0612.9517.13MORL/D2026.066.853.91PCN2026.062.441.68CAPQL2026.060.04—