Safe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence
arXiv:2610.39409v1 Announce Type: cross Abstract: Many applications of multi-objective reinforcement learning (MORL) require policies that balance conflicting objectives while satisfying safety constraints. We study safe MORL with zero constraint violation throughout learning, covering both cumulative and stepwise constraints. A key challenge is to explore sufficiently under unknown dynamics and constraint costs without violating the constraints. For a given preference over objectives, we devel…