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
N1 - Funding Information:
We thank the anonymous reviewers for their helpful feedback. Much of this work was done while Maryam Majzoubi and Chicheng Zhang were visiting Microsoft Research NYC. This work was supported by Microsoft.
Publisher Copyright:
© 2020 Neural information processing systems foundation. All rights reserved.
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 - http://www.scopus.com/inward/record.url?scp=85102100291&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102100291&partnerID=8YFLogxK
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 -