TY - GEN
T1 - Distributionally Robust Path Integral Control
AU - Park, Hyuk
AU - Zhou, Duo
AU - Hanasusanto, Grani A.
AU - Tanaka, Takashi
N1 - Publisher Copyright:
© 2024 AACC.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - distributionally robust optimization
KW - path integral method
KW - risk-sensitive control
KW - stochastic optimal control
UR - http://www.scopus.com/inward/record.url?scp=85204476339&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85204476339&partnerID=8YFLogxK
U2 - 10.23919/ACC60939.2024.10644179
DO - 10.23919/ACC60939.2024.10644179
M3 - Conference contribution
AN - SCOPUS:85204476339
T3 - Proceedings of the American Control Conference
SP - 1164
EP - 1171
BT - 2024 American Control Conference, ACC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 American Control Conference, ACC 2024
Y2 - 10 July 2024 through 12 July 2024
ER -