On-Policy Robust Adaptive Discrete-Time Regulator for Passive Unidirectional System using Stochastic Hill-climbing Algorithm and Associated Search Element

TL;DR

This paper introduces a novel on-policy adaptive discrete-time regulator for passive unidirectional systems, utilizing a stochastic hill-climbing algorithm and an associated search element to improve online parameter tuning and system stability.

Contribution

It proposes a new adaptive regulator that effectively tunes parameters online without offline identification, ensuring stability in passive unidirectional systems.

Findings

Demonstrates effectiveness through simulation results.

Shows robustness in the presence of noise and disturbances.

Validates the approach on two passive systems.

Abstract

Non-linear discrete-time state-feedback regulators are widely used in passive unidirectional systems. Offline system identification is required for tuning parameters of these regulators. However, offline system identification is challenging in some applications. Furthermore, the parameters of a system may be slowly changing over time, which makes the system identification less effective. Many adaptive regulators have been proposed to tune the parameters online when the offline information is neither accessible nor time-invariant. Stability and convergence of these adaptive regulators are challenging, especially in unidirectional systems. In this paper, a novel adaptive regulator is proposed for first-order unidirectional passive systems. In this method, an associated search element checks the eligibility of the update law. Then, a stochastic hill-climbing algorithm updates the parameters of the discrete-time state-feedback regulator. Simulation results demonstrate the effectiveness of the proposed method. The experiments on regulating of two passive systems show the ability of the method in regulating of passive unidirectional system in the presence of noise and disturbance.