Reinforcement learning for control

Performance, stability, and deep approximators

Review (2018)
Author(s)

Lucían Busoniu (Technical University of Cluj-Napoca)

Tim de Bruin (TU Delft - Learning & Autonomous Control)

Domagoj Tolić (RIT Croatia)

Jens Kober (TU Delft - Learning & Autonomous Control)

Ivana Palunko (University of Dubrovnik)

Research Group
Learning & Autonomous Control
Copyright
© 2018 Lucian Buşoniu, T.D. de Bruin, Domagoj Tolić, J. Kober, Ivana Palunko
DOI related publication
https://doi.org/10.1016/j.arcontrol.2018.09.005
More Info
expand_more
Publication Year
2018
Language
English
Copyright
© 2018 Lucian Buşoniu, T.D. de Bruin, Domagoj Tolić, J. Kober, Ivana Palunko
Related content
Research Group
Learning & Autonomous Control
Volume number
46
Pages (from-to)
8-28
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Reinforcement learning (RL) offers powerful algorithms to search for optimal controllers of systems with nonlinear, possibly stochastic dynamics that are unknown or highly uncertain. This review mainly covers artificial-intelligence approaches to RL, from the viewpoint of the control engineer. We explain how approximate representations of the solution make RL feasible for problems with continuous states and control actions. Stability is a central concern in control, and we argue that while the control-theoretic RL subfield called adaptive dynamic programming is dedicated to it, stability of RL largely remains an open question. We also cover in detail the case where deep neural networks are used for approximation, leading to the field of deep RL, which has shown great success in recent years. With the control practitioner in mind, we outline opportunities and pitfalls of deep RL; and we close the survey with an outlook that – among other things – points out some avenues for bridging the gap between control and artificial-intelligence RL techniques.

Files

1_s2.0_S1367578818301184_main.... (pdf)
(pdf | 1.23 Mb)
- Embargo expired in 19-04-2019
License info not available