Distributionally Robust Path Integral Control

Hyuk Park, Duo Zhou, Grani A. Hanasusanto, Takashi Tanaka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider a continuous-time continuous-space stochastic optimal control problem, where the controller lacks exact knowledge of the underlying diffusion process, relying instead on a finite set of historical disturbance trajectories. In situations where data collection is limited, the controller synthesized from empirical data may exhibit poor performance. To address this issue, we introduce a novel approach named Distributionally Robust Path Integral (DRPI). The proposed method employs distributionally robust optimization (DRO) to robustify the resulting policy against the unknown diffusion process. Notably, the DRPI scheme shows similarities with risk-sensitive control, which enables us to utilize the path integral control (PIC) framework as an efficient solution scheme. We derive theoretical performance guarantees for the DRPI scheme, which closely aligns with selecting a risk parameter in risk-sensitive control. We validate the efficacy of our scheme and showcase its superiority when compared to risk-neutral and risk-averse PIC policies in the absence of the true diffusion process.

Original languageEnglish (US)
Title of host publication2024 American Control Conference, ACC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1164-1171
Number of pages8
ISBN (Electronic)9798350382655
DOIs
StatePublished - 2024
Event2024 American Control Conference, ACC 2024 - Toronto, Canada
Duration: Jul 10 2024Jul 12 2024

Publication series

NameProceedings of the American Control Conference
ISSN (Print)0743-1619

Conference

Conference2024 American Control Conference, ACC 2024
Country/TerritoryCanada
CityToronto
Period7/10/247/12/24

Keywords

  • distributionally robust optimization
  • path integral method
  • risk-sensitive control
  • stochastic optimal control

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Distributionally Robust Path Integral Control'. Together they form a unique fingerprint.

Cite this