ResearchBenchmarksMulti-Objective Reinforcement Learning on MO-Ant 2obj v5Multi-Objective Reinforcement Learning on MO-Ant 2obj v5Follow14,600,000HypervolumeMOPDERL11,792,00012,521,00013,250,00013,979,000Mar 3, 2026Evaluation resultsMethodMethodLinksHypervolumeSparsityMOPDERL2026.0314,600,000201.4MORL/D2026.0314,100,000289.8MAPEX2026.0311,900,000315.5