AI RESEARCH
Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORL
arXiv CS.LG
•
ArXi:2508.02217v2 Announce Type: replace Multi-objective reinforcement learning (MORL) is a fundamental framework for real-world decision-making problems involving multiple conflicting criteria. Existing multi-policy (MP) methods typically rely on online evolutionary frameworks that maintain large policy populations, leading to high sample complexity and excessive agent-environment interactions. To mitigate these limitations, we present Multi-policy Pareto Front Tracking (MPFT), a framework without a self-evolving population.