Reinforcement Learning for Adaptive Periodic Linear Quadratic Control

Abstract

This paper presents a first solution to the problem of adaptive LQR for continuous-time linear periodic systems. Specifically, reinforcement learning and adaptive dynamic programming (ADP) techniques are used to develop two algorithms to obtain near-optimal controllers. Firstly, the policy iteration (PI) and value iteration (VI) methods are proposed when the model is known. Then, PI-based and VI-based off-policy ADP algorithms are derived to find near-optimal solutions directly from input/state data collected along the system trajectories, without the exact knowledge of system dynamics. The effectiveness of the derived algorithms is validated using the well-known lossy Mathieu equation.