English

Model-Based Reinforcement Learning for Approximate Optimal Control with Temporal Logic Specifications

Systems and Control 2021-04-16 v2 Systems and Control

Abstract

In this paper we study the problem of synthesizing optimal control policies for uncertain continuous-time nonlinear systems from syntactically co-safe linear temporal logic (scLTL) formulas. We formulate this problem as a sequence of reach-avoid optimal control sub-problems. We show that the resulting hybrid optimal control policy guarantees the satisfaction of a given scLTL formula by constructing a barrier certificate. Since solving each optimal control problem may be computationally intractable, we take a learning-based approach to approximately solve this sequence of optimal control problems online without requiring full knowledge of the system dynamics. Using Lyapunov-based tools, we develop sufficient conditions under which our approximate solution maintains correctness. Finally, we demonstrate the efficacy of the developed method with a numerical example.

Keywords

Cite

@article{arxiv.2101.07156,
  title  = {Model-Based Reinforcement Learning for Approximate Optimal Control with Temporal Logic Specifications},
  author = {Max Cohen and Calin Belta},
  journal= {arXiv preprint arXiv:2101.07156},
  year   = {2021}
}

Comments

To appear at the 24th ACM International Conference on Hybrid Systems: Computation and Control

R2 v1 2026-06-23T22:16:52.148Z