Data-driven control: Recommended further reading

A light introduction (not only) for Matlab and Simulink users: “Reinforcement Learning with MATLAB and Simulink.” The Mathworks. Accessed November 19, 2021. https://www.mathworks.com/campaigns/offers/reinforcement-learning-with-matlab-ebook.html.

A classical reference to which any newcomer to reinforcement learning is automatically directed is

Sutton, Richard S., and Andrew G. Barto. Reinforcement Learning: An Introduction. Second edition. Cambridge, Massachusetts: A Bradford Book, 2018. http://incompleteideas.net/book/the-book-2nd.html.

It is surely a beautiful book. There is a minor trouble with this book, though. It is written from the perspective of a computer scientist. The language and even the selection of examples can make it a little tougher than necessary for a control engineer to get the presented ideas. Anyway, it is a must. The more so that the book is legally available on the authors' website (make sure you get the 2nd edition, it is a major overhaul).

From the perspective of a control engineer, another recent monograph from a (extraordinarily) productive author may be a bit more digestible.

Bertsekas, Dimitri. Reinforcement Learning and Optimal Control. 1st edition. Athena Scientific, 2019.

Although a full version of the book is not available legally online, the author does make some related material available online, including lecture notes covering the extended introduction and some videos.

Reinforcement learning is obviosly a hot research direction today. I am aware of at least three more recent monographs and all three are legally available online, in fact even before they are available in print:

Kochenderfer, Mykel J., Tim A. Wheeler, and Kyle H. Wray. Algorithms for Decision Making. MIT Press, 2022. https://algorithmsbook.com/#download.
Meyn, Sean. Control Systems and Reinforcement Learning. Cambridge University Press, 2022. https://meyn.ece.ufl.edu/2021/08/01/control-systems-and-reinforcement-learning/.
Powell, Warren B. Reinforcement Learning and Stochastic Optimization: A Unified Framework for Sequential Decisions, 2022. https://castlelab.princeton.edu/rlso/.

Lucky those who want to learn the reinfocement learning these days.

Finally, besides the monographs/textbooks, there are also a few tutorial papers (the second and the third in the list are not differing much and constitute a material for a RL chapter in the latest edition of the author's book on optimal control, now also available online on the author's page):

Recht, Benjamin. “A Tour of Reinforcement Learning: The View from Continuous Control.” Annual Review of Control, Robotics, and Autonomous Systems 2, no. 1 (2019): 253–79. https://doi.org/10.1146/annurev-control-053018-023825.In fact, the paper summarizes the content of a blog series: Recht, Benjamin. “An Outsider’s Tour of Reinforcement Learning.” Blog. Arg Min Blog (blog), June 25, 2018. http://benjamin-recht.github.io/2018/06/25/outsider-rl/.
Lewis, Frank L., and Draguna Vrabie. “Reinforcement Learning and Adaptive Dynamic Programming for Feedback Control.” IEEE Circuits and Systems Magazine 9, no. 3 (Third 2009): 32–50. https://doi.org/10.1109/MCAS.2009.933854.
Lewis, Frank L., Draguna Vrabie, and Kyriakos G. Vamvoudakis. “Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers.” IEEE Control Systems Magazine 32, no. 6 (December 2012): 76–105. https://doi.org/10.1109/MCS.2012.2214134.

Last but not least, of the works created by nearest colleagues (at ČVUT in Prague), I link this one

Hauser, Jan, Daniel Pachner, and Vladimír Havlena. “Gaussian Process Based Model-Free Control with Q-Learning.” IFAC-PapersOnLine, 5th IFAC Conference on Intelligent Control and Automation Sciences ICONS 2019, 52, no. 11 (January 1, 2019): 236–43. https://doi.org/10.1016/j.ifacol.2019.09.147.

Naposledy změněno: pátek, 19. listopadu 2021, 16.15