Approximate Solution Methods for the Average Reward Criterion in Optimal Tracking Control of Linear Systems

2025/07/02 by Duc Cuong Nguyen, Nguyen, Duc Cuong
Engineering · #Aerospace Engineering and Control Systems #FOS: Electrical engineering #FOS: Mathematics #Optimization and Control (math.OC) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2507.01556

openalex publication_date 2025/07/02 · openalex created_date 2025/10/20 · openalex updated_date 2026/07/28

Abstract

This paper studies optimal control under the average-reward/cost criterion for deterministic linear systems. We derive the value function and optimal policy, and propose an approximate solution using Model Predictive Control to enable practical implementation.

Citations

• Stable MPC with maximal terminal sets and quadratic terminal costs
• Inverse Reinforcement Learning with the Average Reward Criterion
• Predictive Control with Learning-Based Terminal Costs Using Approximate Value Iteration
• On-Policy Deep Reinforcement Learning for the Average-Reward Criterion
• Stability and performance in MPC using a finite-tail cost
• Reinforcement Learning: An Introduction

Related

• Asymptotic Lower Bounds for Optimal Tracking: a Linear Programming Approach
• Linear Programming Formulation of Long Run Average Optimal Control Problem
• Optimal control with moderation incentives
• Optimal Tracking Control for Unknown Linear Systems with Finite-Time Parameter Estimation
• Constrained Optimal Tracking Control of Unknown Systems: A Multi-Step\n Linear Programming Approach