Data-Driven Dynamic Multiobjective Optimal Control: An Aspiration-Satisfying Reinforcement Learning Approach

This article presents an iterative data-driven algorithm for solving dynamic multiobjective (MO) optimal control problems arising in control of nonlinear continuous-time systems. It is first shown that the Hamiltonian functional corresponding to each objective can be leveraged to compare the perform...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transaction on neural networks and learning systems Ročník 33; číslo 11; s. 6183 - 6193
Hlavní autori: Mazouchi, Majid, Yang, Yongliang, Modares, Hamidreza
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.11.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Algorithms
Continuous time systems
Cost function
Decision making
Inequalities
Iterative algorithms
Linear programming
Machine learning
Multiobjective (MO) optimization
Nonlinear control
Nonlinear systems
of-square program
Optimal control
Optimization
Pareto optimization
Reinforcement
reinforcement learning (RL)
satisficing control
System dynamics
Trajectory
Trajectory measurement
ISSN:2162-237X, 2162-2388, 2162-2388
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This article presents an iterative data-driven algorithm for solving dynamic multiobjective (MO) optimal control problems arising in control of nonlinear continuous-time systems. It is first shown that the Hamiltonian functional corresponding to each objective can be leveraged to compare the performance of admissible policies. Hamiltonian inequalities are then used for which their satisfaction guarantees satisfying the objectives' aspirations. Relaxed Hamilton-Jacobi-Bellman (HJB) equations in terms of HJB inequalities are then solved in a dynamic constrained MO framework to find Pareto optimal solutions. Relation to satisficing (good enough) decision-making framework is shown. A sum-of-square (SOS)-based iterative algorithm is developed to solve the formulated aspiration-satisfying MO optimization. To obviate the requirement of complete knowledge of the system dynamics, a data-driven satisficing reinforcement learning approach is proposed to solve the SOS optimization problem in real time using only the information of the system trajectories measured during a time interval without having full knowledge of the system dynamics. Finally, two simulation examples are utilized to verify the analytical results of the proposed algorithm.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2021.3072571