On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pfrommer, Daniel, Padmanabhan, Swati, Ahn, Kwangjun, Umenberger, Jack, Marcucci, Tobia, Mhammedi, Zakaria, Jadbabaie, Ali
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913489233117184
author Pfrommer, Daniel
Padmanabhan, Swati
Ahn, Kwangjun
Umenberger, Jack
Marcucci, Tobia
Mhammedi, Zakaria
Jadbabaie, Ali
author_facet Pfrommer, Daniel
Padmanabhan, Swati
Ahn, Kwangjun
Umenberger, Jack
Marcucci, Tobia
Mhammedi, Zakaria
Jadbabaie, Ali
contents 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. At the crux of this theoretical guarantee on smoothness is a new lower bound we prove on the optimality gap of the analytic center associated with a convex Lipschitz function, which we hope could be of independent interest. We validate our theoretical findings via experiments, demonstrating the merits of our smoothing approach over randomized smoothing.
format Preprint
id arxiv_https___arxiv_org_abs_2306_01914
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control
Pfrommer, Daniel
Padmanabhan, Swati
Ahn, Kwangjun
Umenberger, Jack
Marcucci, Tobia
Mhammedi, Zakaria
Jadbabaie, Ali
Systems and Control
Machine Learning
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. At the crux of this theoretical guarantee on smoothness is a new lower bound we prove on the optimality gap of the analytic center associated with a convex Lipschitz function, which we hope could be of independent interest. We validate our theoretical findings via experiments, demonstrating the merits of our smoothing approach over randomized smoothing.
title On the Sample Complexity of Imitation Learning for Smoothed Model Predictive Control
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2306.01914