Safe Reinforcement Learning Using Robust MPC

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zanon, Mario, Gros, Sébastien
Natura: Preprint
Pubblicazione: 2019
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914953667018752
author Zanon, Mario
Gros, Sébastien
author_facet Zanon, Mario
Gros, Sébastien
contents 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 partially neglected by the RL community, are central to the control community which 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 paper, we propose to combine RL and MPC in order to exploit the advantages of both and, therefore, obtain a controller which is optimal and safe. We illustrate the results with a numerical example in simulations.
format Preprint
id arxiv_https___arxiv_org_abs_1906_04005
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Safe Reinforcement Learning Using Robust MPC
Zanon, Mario
Gros, Sébastien
Systems and Control
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 partially neglected by the RL community, are central to the control community which 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 paper, we propose to combine RL and MPC in order to exploit the advantages of both and, therefore, obtain a controller which is optimal and safe. We illustrate the results with a numerical example in simulations.
title Safe Reinforcement Learning Using Robust MPC
topic Systems and Control
url https://arxiv.org/abs/1906.04005