Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics

Asaf Cassel; Alon Cohen; Tomer Koren

Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics

Research output: Contribution to journal › Conference article › peer-review

Abstract

We consider the problem of controlling an unknown linear dynamical system under a stochastic convex cost and full feedback of both the state and cost function. We present a computationally efficient algorithm that attains an optimal ^√T regret-rate compared to the best stabilizing linear controller in hindsight. In contrast to previous work, our algorithm is based on the Optimism in the Face of Uncertainty paradigm. This results in a substantially improved computational complexity and a simpler analysis.

Original language	English
Pages (from-to)	3589-3604
Number of pages	16
Journal	Proceedings of Machine Learning Research
Volume	178
State	Published - 2022
Event	35th Conference on Learning Theory, COLT 2022 - London, United Kingdom Duration: 2 Jul 2022 → 5 Jul 2022 https://proceedings.mlr.press/v178

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Software
Control and Systems Engineering
Statistics and Probability

Access to Document

https://proceedings.mlr.press/v178/cassel22a/cassel22a.pdf

Cite this

@article{a0f76b19a290440da4e45e9b6b7265e1,

title = "Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics",

abstract = "We consider the problem of controlling an unknown linear dynamical system under a stochastic convex cost and full feedback of both the state and cost function. We present a computationally efficient algorithm that attains an optimal √T regret-rate compared to the best stabilizing linear controller in hindsight. In contrast to previous work, our algorithm is based on the Optimism in the Face of Uncertainty paradigm. This results in a substantially improved computational complexity and a simpler analysis.",

author = "Asaf Cassel and Alon Cohen and Tomer Koren",

note = "Publisher Copyright: {\textcopyright} 2022 A. Cassel, A. Cohen & T. Koren.; 35th Conference on Learning Theory, COLT 2022 ; Conference date: 02-07-2022 Through 05-07-2022",

year = "2022",

language = "الإنجليزيّة",

volume = "178",

pages = "3589--3604",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

url = "https://proceedings.mlr.press/v178",

}

TY - JOUR

T1 - Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics

AU - Cassel, Asaf

AU - Cohen, Alon

AU - Koren, Tomer

PY - 2022

Y1 - 2022

N2 - We consider the problem of controlling an unknown linear dynamical system under a stochastic convex cost and full feedback of both the state and cost function. We present a computationally efficient algorithm that attains an optimal √T regret-rate compared to the best stabilizing linear controller in hindsight. In contrast to previous work, our algorithm is based on the Optimism in the Face of Uncertainty paradigm. This results in a substantially improved computational complexity and a simpler analysis.

AB - We consider the problem of controlling an unknown linear dynamical system under a stochastic convex cost and full feedback of both the state and cost function. We present a computationally efficient algorithm that attains an optimal √T regret-rate compared to the best stabilizing linear controller in hindsight. In contrast to previous work, our algorithm is based on the Optimism in the Face of Uncertainty paradigm. This results in a substantially improved computational complexity and a simpler analysis.

UR - http://www.scopus.com/inward/record.url?scp=85164708607&partnerID=8YFLogxK

M3 - مقالة من مؤنمر

SN - 2640-3498

VL - 178

SP - 3589

EP - 3604

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 35th Conference on Learning Theory, COLT 2022

Y2 - 2 July 2022 through 5 July 2022

ER -

Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this