Distributionally Robust Constrained Reinforcement Learning under Strong Duality

arXiv:2406.15788v1 Announce Type: new
Abstract: We study the problem of Distributionally Robust Constrained RL (DRC-RL), where the goal is to maximize the expected reward subject to environmental distribution shifts and constraints. This setting captures situations where training and testing environments differ, and policies must satisfy constraints motivated by safety or limited budgets. Despite significant progress toward algorithm design for the separate problems of distributionally robust RL and constrained RL, there do not yet exist algorithms with end-to-end convergence guarantees for …

abstract arxiv budgets constraints cs.lg distribution environmental environments policies problem reinforcement reinforcement learning robust safety study testing training type