ResearchBenchmarksMulti-Objective Reinforcement Learning on MinecartMulti-Objective Reinforcement Learning on MinecartFollow7.39Hypervolume (HV)D3PO5.23725.79616.3556.9139Feb 8, 2026Evaluation resultsMethodMethodLinksHypervolume (HV)Expected Utility (EU)Sparsity (SP)Compute Time (hours)D3PO2026.027.391.917C-MORL2026.026.772.12516GPI-LS2026.026.052.29105PCN2026.025.321.5106