Learning Expected Reward for Switched Linear Control Systems: A Non-Asymptotic View
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 $\mathbb{R}^{n}$. 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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generalized Cactus and Structural Controllability of Switched Linear Continuous-Time Systems
This paper explores the structural controllability of switched linear continuous-time systems. It first identifies a gap in the proof for a pivotal criterion for the structural controllability of switched linear systems …
Contouring Error Bounded Control for Biaxial Switched Linear Systems
Biaxial motion control systems are used extensively in manufacturing and printing industries. To improve throughput and reduce machine cost, lightweight materials are being proposed in structural components but may resul…
Model Predictive ControlPositionNonlinear Negative Imaginary Systems with Switching
In this paper, we extend nonlinear negative imaginary (NI) systems theory to switched systems. Switched nonlinear NI systems and switched nonlinear output strictly negative imaginary (OSNI) systems are defined. We show t…
Stabilization of Switched Affine Systems With Dwell-Time Constraint
This paper addresses the problem of stabilization of switched affine systems under dwell-time constraint, giving guarantees on the bound of the quadratic cost associated with the proposed state switching control law. Spe…
Robust performance for switched systems with constrained switching and its application to weakly hard real-time control systems
Many cyber-physical systems can naturally be formulated as switched systems with constrained switching. This includes systems where one of the signals in the feedback loop may be lost. Possible sources for losses are sha…