Efficient contextual bandits with continuous actions

Maryam Majzoubi; Chicheng Zhang; Rajan Chari; Akshay Krishnamurthy; John Langford; Aleksandrs Slivkins

Efficient contextual bandits with continuous actions

Maryam Majzoubi
, Chicheng Zhang
, Rajan Chari
, Akshay Krishnamurthy
, John Langford
, Aleksandrs Slivkins

Computer Science

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

24 Scopus citations

Abstract

We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised learning representations. We prove that it works in a general sense and verify the new functionality with large-scale experiments.

Original language	English (US)
Journal	Advances in Neural Information Processing Systems
Volume	2020-December
State	Published - 2020
Event	34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online Duration: Dec 6 2020 → Dec 12 2020

ASJC Scopus subject areas

Signal Processing
Information Systems
Computer Networks and Communications

Cite this

@article{7f4d99315c974a11878be6003d1b0c7a,

title = "Efficient contextual bandits with continuous actions",

abstract = "We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised learning representations. We prove that it works in a general sense and verify the new functionality with large-scale experiments.",

author = "Maryam Majzoubi and Chicheng Zhang and Rajan Chari and Akshay Krishnamurthy and John Langford and Aleksandrs Slivkins",

note = "Publisher Copyright: {\textcopyright} 2020 Neural information processing systems foundation. All rights reserved.; 34th Conference on Neural Information Processing Systems, NeurIPS 2020 ; Conference date: 06-12-2020 Through 12-12-2020",

year = "2020",

language = "English (US)",

volume = "2020-December",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

T1 - Efficient contextual bandits with continuous actions

AU - Majzoubi, Maryam

AU - Zhang, Chicheng

AU - Chari, Rajan

AU - Krishnamurthy, Akshay

AU - Langford, John

AU - Slivkins, Aleksandrs

PY - 2020

Y1 - 2020

N2 - We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised learning representations. We prove that it works in a general sense and verify the new functionality with large-scale experiments.

AB - We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised learning representations. We prove that it works in a general sense and verify the new functionality with large-scale experiments.

UR - https://www.scopus.com/pages/publications/85102100291

UR - https://www.scopus.com/pages/publications/85102100291#tab=citedBy

M3 - Conference article

AN - SCOPUS:85102100291

SN - 1049-5258

VL - 2020-December

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 34th Conference on Neural Information Processing Systems, NeurIPS 2020

Y2 - 6 December 2020 through 12 December 2020

ER -

Efficient contextual bandits with continuous actions

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this