ResearchBenchmarksMulti-Objective Reinforcement Learning on mo-hopper v4Multi-Objective Reinforcement Learning on mo-hopper v4Follow0.5888Normalised Hypervolume (HV)MERLION-0.0210560.1372720.29560.453928Jun 20, 2026Evaluation resultsMethodMethodLinksNormalised Hypervolume (HV)SparsityMERLION2026.060.58880.1158Meta-MORL2026.060.0520.0073MORL/D2026.060.01380.001CAPQL2026.060.00690.0003PGMORL2026.060.00580.0037PCN2026.060.00240.002