Causal bandits: Learning good interventions via causal inference

Finnian Lattimore; Tor Lattimore; Mark D. Reid

Causal bandits: Learning good interventions via causal inference

Finnian Lattimore, Tor Lattimore, Mark D. Reid

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

79 Citations (Scopus)

Abstract

We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm that exploits the causal feedback and prove a bound on its simple regret that is strictly better (in all quantities) than algorithms that do not use the additional causal information.

Original language	English
Pages (from-to)	1189-1197
Number of pages	9
Journal	Advances in Neural Information Processing Systems
Publication status	Published - 2016
Event	30th Annual Conference on Neural Information Processing Systems, NIPS 2016 - Barcelona, Spain Duration: 5 Dec 2016 → 10 Dec 2016

Cite this

@article{062817973f544f0b85de0ef0fd1fd8ac,

title = "Causal bandits: Learning good interventions via causal inference",

abstract = "We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm that exploits the causal feedback and prove a bound on its simple regret that is strictly better (in all quantities) than algorithms that do not use the additional causal information.",

author = "Finnian Lattimore and Tor Lattimore and Reid, {Mark D.}",

note = "Publisher Copyright: {\textcopyright} 2016 NIPS Foundation - All Rights Reserved.; 30th Annual Conference on Neural Information Processing Systems, NIPS 2016 ; Conference date: 05-12-2016 Through 10-12-2016",

year = "2016",

language = "English",

pages = "1189--1197",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

T1 - Causal bandits

T2 - 30th Annual Conference on Neural Information Processing Systems, NIPS 2016

AU - Lattimore, Finnian

AU - Lattimore, Tor

AU - Reid, Mark D.

PY - 2016

Y1 - 2016

N2 - We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm that exploits the causal feedback and prove a bound on its simple regret that is strictly better (in all quantities) than algorithms that do not use the additional causal information.

AB - We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit feedback that is not exploited by existing approaches. We propose a new algorithm that exploits the causal feedback and prove a bound on its simple regret that is strictly better (in all quantities) than algorithms that do not use the additional causal information.

UR - http://www.scopus.com/inward/record.url?scp=85019215870&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85019215870

SN - 1049-5258

SP - 1189

EP - 1197

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

Y2 - 5 December 2016 through 10 December 2016

ER -

Causal bandits: Learning good interventions via causal inference

Abstract

Other files and links

Cite this