Skip navigation
Skip navigation

Causal Bandits: Learning Good Interventions via Causal Inference

Lattimore, Finnian Rachel; Lattimore, Tor; Reid, Mark

Description

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...[Show more]

dc.contributor.authorLattimore, Finnian Rachel
dc.contributor.authorLattimore, Tor
dc.contributor.authorReid, Mark
dc.contributor.editorLee, D. D.
dc.contributor.editorSugiyama, M.
dc.contributor.editorLuxburg, U. V.
dc.contributor.editorGuyon, I.
dc.contributor.editorGarnett, R.
dc.coverage.spatialBarcelona, Spain
dc.date.accessioned2019-11-25T00:04:04Z
dc.date.createdDecember 5-10 2016
dc.identifier.isbn9781510838819
dc.identifier.urihttp://hdl.handle.net/1885/186528
dc.description.abstractWe 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
dc.format.mimetypeapplication/pdf
dc.language.isoen_AU
dc.publisherNeural Information Processing Systems Foundation
dc.relation.ispartofseries30th Annual Conference on Neural Information Processing Systems, NIPS 2016
dc.rights© 2016 individual authors and NIPS
dc.sourceAdvances in Neural Information Processing Systems 29: 30th Annual Conference on Neural Information Processing Systems 2016
dc.titleCausal Bandits: Learning Good Interventions via Causal Inference
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2016
local.identifier.absfor170203 - Knowledge Representation and Machine Learning
local.identifier.ariespublicationa383154xPUB6104
local.type.statusPublished Version
local.contributor.affiliationLattimore, Finnian, College of Engineering and Computer Science, ANU
local.contributor.affiliationLattimore, Tor, University of Alberta
local.contributor.affiliationReid, Mark, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.identifier.absseo970108 - Expanding Knowledge in the Information and Computing Sciences
dc.date.updated2019-05-19T08:19:39Z
local.identifier.scopusID2-s2.0-85019215870
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Lattimore_Causal_Bandits%3A_Learning_Good_2016.pdf1.5 MBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator