Solving mixed influence diagrams by reinforcement learning

Simple item page
dc.contributor.authorPrestwich, Steven D.en
dc.contributor.funderScience Foundation Irelanden
dc.contributor.funderEuropean Regional Development Funden
dc.contributor.funderHorizon 2020en
dc.date.accessioned2024-07-10T12:37:33Z
dc.date.available2024-07-10T12:37:33Z
dc.date.issued2024-02-15en
dc.description.abstractWhile efficient optimisation methods exist for problems with special properties (linear, continuous, differentiable, unconstrained), real-world problems often involve inconvenient complications (constrained, discrete, multi-stage, multi-level, multi-objective). Each of these complications has spawned research areas in Artificial Intelligence and Operations Research, but few methods are available for hybrid problems. We describe a reinforcement learning-based solver for a broad class of discrete problems that we call Mixed Influence Diagrams, which may have multiple stages, multiple agents, multiple non-linear objectives, correlated chance variables, exogenous and endogenous uncertainty, constraints (hard, soft and chance) and partially observed variables. We apply the solver to problems taken from stochastic programming, chance-constrained programming, limited-memory influence diagrams, multi-level and multi-objective optimisation. We expect the approach to be useful on new hybrid problems for which no specialised solution methods exist.en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationPrestwich, S.D. (2024) ‘Solving mixed influence diagrams by reinforcement learning’, in G. Nicosia, V. Ojha, E. La Malfa, G. La Malfa, P.M. Pardalos, and R. Umeton (eds) Machine Learning, Optimization, and Data Science, LOD 2023. Lecture Notes in Computer Science, vol 14506. Springer, Cham, pp. 255–269. https://doi.org/10.1007/978-3-031-53966-4_19en
dc.identifier.doi10.1007/978-3-031-53966-4_19en
dc.identifier.endpage269en
dc.identifier.isbn9783031539657en
dc.identifier.isbn9783031539664en
dc.identifier.issn0302-9743en
dc.identifier.issn1611-3349en
dc.identifier.journaltitleLecture Notes in Computer Scienceen
dc.identifier.startpage255en
dc.identifier.urihttps://hdl.handle.net/10468/16116
dc.identifier.volume14506en
dc.language.isoenen
dc.publisherSpringeren
dc.relation.ispartofMachine Learning, Optimization, and Data Scienceen
dc.relation.ispartofLecture Notes in Computer Scienceen
dc.relation.ispartofThe 9th International Conference on Machine Learning, Optimization, and Data Science, LOD 23en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres Programme::Phase 1/16/RC/3918/IE/Confirm Centre for Smart Manufacturing/en
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::RIA/952215/EU/Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization/TAILORen
dc.rights© the authors 2024. This is a post-peer-review, pre-copyedit version of a paper published as: Prestwich, S.D. (2024). Solving Mixed Influence Diagrams by Reinforcement Learning, LOD 2023. Lecture Notes in Computer Science, vol 14506. The final authenticated version is available online at: https://doi.org/10.1007/978-3-031-53966-4_19en
dc.subjectArtificial Intelligence (AI)en
dc.subjectOptimisationen
dc.subjectReinforcement learningen
dc.subjectMixed Influence Diagramsen
dc.subjectOperations researchen
dc.titleSolving mixed influence diagrams by reinforcement learningen
dc.typeArticle (peer-reviewed)en
dc.typebook-chapteren
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
lod23.pdf
Size:
247.82 KB
Format:
Adobe Portable Document Format
Description:
Accepted version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Journal Articles