English

On Convex Data-Driven Inverse Optimal Control for Nonlinear, Non-stationary and Stochastic Systems

Optimization and Control 2024-06-27 v2 Information Theory Machine Learning Robotics Dynamical Systems math.IT

Abstract

This paper is concerned with a finite-horizon inverse control problem, which has the goal of reconstructing, from observations, the possibly non-convex and non-stationary cost driving the actions of an agent. In this context, we present a result enabling cost reconstruction by solving an optimization problem that is convex even when the agent cost is not and when the underlying dynamics is nonlinear, non-stationary and stochastic. To obtain this result, we also study a finite-horizon forward control problem that has randomized policies as decision variables. We turn our findings into algorithmic procedures and show the effectiveness of our approach via in-silico and hardware validations. All experiments confirm the effectiveness of our approach.

Keywords

Cite

@article{arxiv.2306.13928,
  title  = {On Convex Data-Driven Inverse Optimal Control for Nonlinear, Non-stationary and Stochastic Systems},
  author = {Emiland Garrabe and Hozefa Jesawada and Carmen Del Vecchio and Giovanni Russo},
  journal= {arXiv preprint arXiv:2306.13928},
  year   = {2024}
}

Comments

17 pages, 5 figures. An early version of this paper with only a sketch of the proof for one of the results and without the hardware validation was presentation at the 62nd IEEE Conference on Decision and Control. arXiv admin note: text overlap with arXiv:2303.17957

R2 v1 2026-06-28T11:13:25.496Z