Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables stronger guarantees on the performance of the learned controller. However, constructing such smoothed expert controllers for arbitrary systems remains challenging, especially in the presence of input and state constraints. As our primary contribution, we show how such a smoothed expert can be designed for a general class of systems using a log-barrier-based relaxation of a standard Model Predictive Control (MPC) optimization problem. Improving upon our previous work, we show that barrier MPC achieves theoretically optimal error-to-smoothness tradeoff along some direction. At the core of this theoretical guarantee on smoothness is an improved lower bound we prove on the optimality gap of the analytic center associated with a convex Lipschitz function, which we believe could be of independent interest. We validate our theoretical findings via experiments, demonstrating the merits of our smoothing approach over randomized smoothing.
@article{arxiv.2410.00859,
title = {Improved Sample Complexity of Imitation Learning for Barrier Model Predictive Control},
author = {Daniel Pfrommer and Swati Padmanabhan and Kwangjun Ahn and Jack Umenberger and Tobia Marcucci and Zakaria Mhammedi and Ali Jadbabaie},
journal= {arXiv preprint arXiv:2410.00859},
year = {2024}
}
Comments
36 pages, 3 figures. This work extends our previous result in arXiv:2306.01914, which has been accepted for publication in CDC 2024. An earlier version of this manuscript was submitted as part of DP's Master's thesis