Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems

arXiv:2403.04007v1 Announce Type: new
Abstract: We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of control theory and the convergence guarantees of RL theory. Recent advances at the intersection of control and RL follow a two-stage, safety filter approach to enforcing hard safety constraints: model-free RL is used to learn a potentially unsafe controller, whose actions are projected onto safe sets prescribed, for example, by …

abstract advances algorithms arxiv control convergence cs.lg gap intersection math.oc reinforcement reinforcement learning safety sampling stage systems theory type