English

Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions

Machine Learning 2022-11-10 v4 Systems and Control Systems and Control

Abstract

This paper develops a model-based reinforcement learning (MBRL) framework for learning online the value function of an infinite-horizon optimal control problem while obeying safety constraints expressed as control barrier functions (CBFs). Our approach is facilitated by the development of a novel class of CBFs, termed Lyapunov-like CBFs (LCBFs), that retain the beneficial properties of CBFs for developing minimally-invasive safe control policies while also possessing desirable Lyapunov-like qualities such as positive semi-definiteness. We show how these LCBFs can be used to augment a learning-based control policy to guarantee safety and then leverage this approach to develop a safe exploration framework in a MBRL setting. We demonstrate that our approach can handle more general safety constraints than comparative methods via numerical examples.

Keywords

Cite

@article{arxiv.2104.08171,
  title  = {Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functions},
  author = {Max H. Cohen and Calin Belta},
  journal= {arXiv preprint arXiv:2104.08171},
  year   = {2022}
}

Comments

Accepted for publication in Automatica

R2 v1 2026-06-24T01:14:55.318Z