ResearchBenchmarksMulti-Objective Reinforcement Learning on FT-6Multi-Objective Reinforcement Learning on FT-6Follow5.02Hypervolume (HV)SPFT3.5123.90354.2954.6865Aug 4, 2025Evaluation resultsMethodMethodLinksHypervolume (HV)Scalarized Performance (SP)Expected Utility (EU)Environment StepsSPFT2025.085.020.56.5967,200C-MORL2025.083.670.426.53500,000Envelope2025.083.665.466.15500,000GPI-LS2025.083.575.296.15500,000