ResearchBenchmarksMulti-Objective Reinforcement Learning on Fruit Tree NavigationFollow5.08UTOptimal4.15444.39474.6354.8753Apr 27, 2026Evaluation ResultsMethodMethodLinksUTHVEDOptimal2026.045.081.25—Envelope2026.045.071.160.95PD-MORLinterpolator=withinterpolator=with2026.045.031.250.76MORL-FB2026.045.011.16—PCN2026.0451.010.72SFOLS2026.044.770.870.08MORL/D2026.044.190.180.01