ResearchBenchmarksMulti-objective Reinforcement Learning on Fruit TreeMulti-objective Reinforcement Learning on Fruit TreeFollow3.57Hypervolume (HV)GPI-LS3.4143.45453.4953.5355Feb 8, 2026Evaluation resultsMethodMethodLinksHypervolume (HV)Expected Utility (EU)Spread (SP)GPI-LS2026.023.576.155.29C-MORL2026.023.526.530.14D3PO2026.023.424.620.04