English

A Test-Function Approach to Incremental Stability

Machine Learning 2025-09-19 v2 Systems and Control Systems and Control

Abstract

This paper presents a novel framework for analyzing Incremental-Input-to-State Stability (δ\deltaISS) based on the idea of using rewards as "test functions." Whereas control theory traditionally deals with Lyapunov functions that satisfy a time-decrease condition, reinforcement learning (RL) value functions are constructed by exponentially decaying a Lipschitz reward function that may be non-smooth and unbounded on both sides. Thus, these RL-style value functions cannot be directly understood as Lyapunov certificates. We develop a new equivalence between a variant of incremental input-to-state stability of a closed-loop system under given a policy, and the regularity of RL-style value functions under adversarial selection of a H\"older-continuous reward function. This result highlights that the regularity of value functions, and their connection to incremental stability, can be understood in a way that is distinct from the traditional Lyapunov-based approach to certifying stability in control theory.

Keywords

Cite

@article{arxiv.2507.00695,
  title  = {A Test-Function Approach to Incremental Stability},
  author = {Daniel Pfrommer and Max Simchowitz and Ali Jadbabaie},
  journal= {arXiv preprint arXiv:2507.00695},
  year   = {2025}
}

Comments

8 pages; updated stability definitions