Safe Reinforcement Learning Using Robust MPC

Reinforcement learning (RL) has recently impressed the world with stunning results in various applications. While the potential of RL is now well established, many critical aspects still need to be tackled, including safety and stability issues. These issues, while secondary for the RL community, ar...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on automatic control Ročník 66; číslo 8; s. 3638 - 3652
Hlavní autori: Zanon, Mario, Gros, Sebastien
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.08.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Computational modeling
Data models
Learning
Model accuracy
Numerical models
Optimization
Predictive control
Reinforcement learning (RL)
robust model predictive control (MPC)
Robustness
Robustness (mathematics)
safe policies
Safety
Stability analysis
Uncertainty
ISSN:0018-9286, 1558-2523
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Reinforcement learning (RL) has recently impressed the world with stunning results in various applications. While the potential of RL is now well established, many critical aspects still need to be tackled, including safety and stability issues. These issues, while secondary for the RL community, are central to the control community that has been widely investigating them. Model predictive control (MPC) is one of the most successful control techniques because, among others, of its ability to provide such guarantees even for uncertain constrained systems. Since MPC is an optimization-based technique, optimality has also often been claimed. Unfortunately, the performance of MPC is highly dependent on the accuracy of the model used for predictions. In this article, we propose to combine RL and MPC in order to exploit the advantages of both, and therefore, obtain a controller that is optimal and safe. We illustrate the results with two numerical examples in simulations.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9286
1558-2523
DOI:10.1109/TAC.2020.3024161