From Supervised to Reinforcement Learning: an Inverse Optimization Approach

Master thesis (2021)

Authors

I. Dimanidis Mechanical Engineering

Contributors

P. Mohajerin Esfahani Team Bart De Schutter - Mechanical, Maritime and Materials Engineering (mentor)
M. Mazo Team Manuel Mazo Jr - Mechanical, Maritime and Materials Engineering (graduation committee member)
B. Atasoy Transport Engineering and Logistics - Mechanical, Maritime and Materials Engineering (graduation committee member)
Faculty
Mechanical Engineering, Mechanical Engineering
Copyright: © 2021 Ioannis Dimanidis
More Info
expand_more

Published Date

10-12-2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical Engineering

Abstract

We propose a novel method combining elements of supervised- and Q-learning for the control of dynamical systems subject to unknown disturbances. By using the Inverse Optimization framework and in-hindsight information we can derive a causal parametric optimization policy that approximates a non-causal MPC expert. Furthermore, we propose a new min-max MPC scheme that robustifies against a ball around a disturbance trajectory. This scheme yields an exact convex reformulation using the S-Lemma, and is also approximated using Inverse Optimization. Finally, simulation studies clarify and verify our approach.

Files

Main.pdf
(pdf | 1.35 Mb)
Unknown license