A view on learning robust goal-conditioned value functions: Interplay between RL and MPC
Annual Reviews in Control, Vol. 59, pp. 101027,
Nathan P. Lawrence, Philip D. Loewen, Michael G. Forbes, R. Bhushan Gopaluni, Ali Mesbah
Abstract
This paper presents a unified framework treating RL and MPC as alternative approaches to solving Markov decision processes, combining robustness and goal-conditioned learning for safe and efficient control policies.