Model predictive control with stage cost shaping inspired by reinforcement learning

2019/06/06 by Beckenbach, Lukas, Osinenko, Pavel, Streif, Stefan
#93C10 #93C40 #93C55 #Dynamical Systems (math.DS) #FOS: Electrical engineering #FOS: Mathematics #Optimization and Control (math.OC) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1906.02580

Abstract

This work presents a suboptimality study of a particular model predictive control with a stage cost shaping based on the ideas of reinforcement learning. The focus of the suboptimality study is to derive quantities relating the infinite-horizon cost function under the said variant of model predictive control to the respective infinite-horizon value function. The basis control scheme involves usual stabilizing constraints comprising of a terminal set and a terminal cost in the form of a local Lyapunov function. The stage cost is adapted using the principles of Q-learning, a particular approach to reinforcement learning. The work is concluded by case studies with two systems for wide ranges of initial conditions.

Related

• Predictive Control with Learning-Based Terminal Costs Using Approximate Value Iteration
• Approximate infinite-horizon predictive control
• Reinforcement Learning of the Prediction Horizon in Model Predictive\n Control
• Equivalence of Optimality Criteria for Markov Decision Process and Model Predictive Control
• Optimization of the Model Predictive Control Update Interval Using\n Reinforcement Learning