English

Stability-certified reinforcement learning: A control-theoretic perspective

Systems and Control 2018-10-30 v1 Machine Learning

Abstract

We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing controllers by exploiting problem-specific structures; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two decentralized control tasks, namely multi-flight formation and power system frequency regulation, demonstrate that the reinforcement learning agents can have high performance within the stability-certified parameter space, and also exhibit stable learning behaviors in the long run.

Keywords

Cite

@article{arxiv.1810.11505,
  title  = {Stability-certified reinforcement learning: A control-theoretic perspective},
  author = {Ming Jin and Javad Lavaei},
  journal= {arXiv preprint arXiv:1810.11505},
  year   = {2018}
}
R2 v1 2026-06-23T04:54:08.885Z