Learning Expected Reward for Switched Linear Control Systems: A Non-Asymptotic View
Probability
2020-06-16 v1 Machine Learning
Systems and Control
Systems and Control
Abstract
In this work, we show existence of invariant ergodic measure for switched linear dynamical systems (SLDSs) under a norm-stability assumption of system dynamics in some unbounded subset of . Consequently, given a stationary Markov control policy, we derive non-asymptotic bounds for learning expected reward (w.r.t the invariant ergodic measure our closed-loop system mixes to) from time-averages using Birkhoff's Ergodic Theorem. The presented results provide a foundation for deriving non-asymptotic analysis for average reward-based optimal control of SLDSs. Finally, we illustrate the presented theoretical results in two case-studies.
Cite
@article{arxiv.2006.08105,
title = {Learning Expected Reward for Switched Linear Control Systems: A Non-Asymptotic View},
author = {Muhammad Abdullah Naeem and Miroslav Pajic},
journal= {arXiv preprint arXiv:2006.08105},
year = {2020}
}