Risk-Sensitive Inhibitory Control for Safe Reinforcement Learning

Armin Lederer, Erfaun Noorani, John S. Baras, Sandra Hirche

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

Abstract

Humans have the ability to deviate from their natural behavior when necessary, which is a cognitive process called response inhibition. Similar approaches have independently received increasing attention in recent years for ensuring the safety of control. Realized using control barrier functions or predictive safety filters, these approaches can effectively ensure the satisfaction of state constraints through an online adaptation of nominal control laws, e.g., obtained through reinforcement learning. While the focus of these realizations of inhibitory control has been on risk-neutral formulations, human studies have shown a tight link between response inhibition and risk attitude. Inspired by this insight, we propose a flexible, risk-sensitive method for inhibitory control. Our method is based on a risk-aware condition for value functions, which guarantees the satisfaction of state constraints. We propose a method for learning these value functions using common techniques from reinforcement learning and derive sufficient conditions for its success. By enforcing the derived safety conditions online using the learned value function, risk-sensitive inhibitory control is effectively achieved. The effectiveness of the developed control scheme is demonstrated in simulations.

OriginalspracheEnglisch
Titel2023 62nd IEEE Conference on Decision and Control, CDC 2023
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten1040-1045
Seitenumfang6
ISBN (elektronisch)9798350301243
DOIs
PublikationsstatusVeröffentlicht - 2023
Veranstaltung62nd IEEE Conference on Decision and Control, CDC 2023 - Singapore, Singapur
Dauer: 13 Dez. 202315 Dez. 2023

Publikationsreihe

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0743-1546
ISSN (elektronisch)2576-2370

Konferenz

Konferenz62nd IEEE Conference on Decision and Control, CDC 2023
Land/GebietSingapur
OrtSingapore
Zeitraum13/12/2315/12/23

Fingerprint

Untersuchen Sie die Forschungsthemen von „Risk-Sensitive Inhibitory Control for Safe Reinforcement Learning“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren