TY - GEN
T1 - Value Iteration and Data-Driven Optimal Output Regulation of Linear Continuous-Time Systems
AU - Jiang, Yi
AU - Gao, Weinan
PY - 2022/8
Y1 - 2022/8
N2 - This paper investigates the linear optimal output regulation problem (LO2RP). We propose a reinforcement learning (RL) based approach to learn the optimal regulator. This problem is solved by tackling two optimization problems, a static constrained optimization problem to find the optimal solution to the output regulation equations and a dynamic programming to obtain the optimal feedback control gain. Instead of relying on the prior knowledge of the system dynamics and an initial stabilizing feedback control gain, a novel online value iteration (VI) algorithm is proposed, which can learn the optimal feedback control gain and feedforward control gain using measurable data. Finally, numerical analysis is provided to show that the proposed approach results in desired disturbance rejection and tracking performance. © 2022 IEEE.
AB - This paper investigates the linear optimal output regulation problem (LO2RP). We propose a reinforcement learning (RL) based approach to learn the optimal regulator. This problem is solved by tackling two optimization problems, a static constrained optimization problem to find the optimal solution to the output regulation equations and a dynamic programming to obtain the optimal feedback control gain. Instead of relying on the prior knowledge of the system dynamics and an initial stabilizing feedback control gain, a novel online value iteration (VI) algorithm is proposed, which can learn the optimal feedback control gain and feedforward control gain using measurable data. Finally, numerical analysis is provided to show that the proposed approach results in desired disturbance rejection and tracking performance. © 2022 IEEE.
KW - optimal output regulation
KW - Reinforcement learning (RL)
KW - value iteration (VI)
UR - http://www.scopus.com/inward/record.url?scp=85149556710&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85149556710&origin=recordpage
U2 - 10.1109/CCDC55256.2022.10033453
DO - 10.1109/CCDC55256.2022.10033453
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 978-1-6654-7897-7
T3 - Proceedings of the Chinese Control and Decision Conference, CCDC
SP - 1509
EP - 1514
BT - Proceedings of the 34th Chinese Control and Decision Conference
PB - IEEE
T2 - 34th Chinese Control and Decision Conference, CCDC 2022
Y2 - 15 August 2022 through 17 August 2022
ER -