Abstract
In this paper, a novel optimal control over finite horizon has been introduced for linear continuous-time systems by using adaptive dynamic programming (ADP). First, a new time-varying Q-function parameterization and its estimator are introduced. Subsequently, Q-function estimator is tuned online by using both Bellman equation in integral form and terminal cost. Eventually, near optimal control gain is obtained by using the Q-function estimator. All the closed-loop signals are shown to be bounded by using Lyapunov stability analysis where bounds are functions of initial conditions and final time while the estimated control signal converges close to the optimal value. The simulation results illustrate the effectiveness of the proposed scheme.
Recommended Citation
H. Xu and S. Jagannathan, "Model-free Q-learning over Finite Horizon for Uncertain Linear Continuous-time Systems," IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - ADPRL 2014: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Proceedings, article no. 7010629, Institute of Electrical and Electronics Engineers, Jan 2014.
The definitive version is available at https://doi.org/10.1109/ADPRL.2014.7010629
Department(s)
Electrical and Computer Engineering
Second Department
Computer Science
Keywords and Phrases
Adaptive Dynamics Programming (ADP); Forward-in-time; Optimal Control; Q-learning; Riccati Equation
International Standard Book Number (ISBN)
978-147994553-5
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
14 Jan 2014
