ResearchBenchmarksMulti-Objective Reinforcement Learning on mo-halfcheetah v4Multi-Objective Reinforcement Learning on mo-halfcheetah v4Follow74.32Normalised Hypervolume (HV)Meta-MORL-1.048818.518138.08557.6519Jun 20, 2026Evaluation resultsMethodMethodLinksNormalised Hypervolume (HV)SparsityMeta-MORL2026.0674.322.01MERLION2026.0641.814.05MORL/D2026.0622.40.04CAPQL2026.0619.810.01PGMORL2026.063.750.02PCN2026.061.850