Model Predictive Q-Learning (MPQ-L) for Bilinear Systems

Minh Q. Phan () and Seyed Mahdi B. Azad ()
Additional contact information
Minh Q. Phan: Dartmouth College, Thayer School of Engineering
Seyed Mahdi B. Azad: Dartmouth College, Thayer School of Engineering

A chapter in Modeling, Simulation and Optimization of Complex Processes HPSC 2018, 2021, pp 97-115 from Springer

Abstract: Abstract This paper provides a conceptual framework to design an optimal controller for a bilinear system by reinforcement learning. Model Predictive Q-Learning (MPQ-L) combines Model Predictive Control (MPC) with Q-Learning. MPC finds an initial sub-optimal controller from which a suitable parameterization of the Q-function is determined. The Q-function and the controller are then updated by reinforcement learning to optimality.

Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-55240-4_5

Ordering information: This item can be ordered from
http://www.springer.com/9783030552404

DOI: 10.1007/978-3-030-55240-4_5

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().