Back to Search
Start Over
Optimal and Autonomous Control Using Reinforcement Learning: A Survey.
- Source :
-
IEEE Transactions on Neural Networks & Learning Systems . Jun2018, Vol. 29 Issue 6, p2042-2062. 21p. - Publication Year :
- 2018
-
Abstract
- This paper reviews the current state of the art on reinforcement learning (RL)-based feedback control solutions to optimal regulation and tracking of single and multiagent systems. Existing RL solutions to both optimal \mathcal H2 and \mathcal H_\infty control problems, as well as graphical games, will be reviewed. RL methods learn the solution to optimal control and game problems online and using measured data along the system trajectories. We discuss Q-learning and the integral RL algorithm as core algorithms for discrete-time (DT) and continuous-time (CT) systems, respectively. Moreover, we discuss a new direction of off-policy RL for both CT and DT systems. Finally, we review several applications. [ABSTRACT FROM AUTHOR]
- Subjects :
- *REINFORCEMENT learning
*ARTIFICIAL intelligence
*MACHINE learning
Subjects
Details
- Language :
- English
- ISSN :
- 2162237X
- Volume :
- 29
- Issue :
- 6
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Neural Networks & Learning Systems
- Publication Type :
- Periodical
- Accession number :
- 129655424
- Full Text :
- https://doi.org/10.1109/TNNLS.2017.2773458