Optimal control as a graphical model inference problem
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Kappen, Hilbert J.
- dc.contributor.author Gómez, Vicenç
- dc.contributor.author Opper, Manfred
- dc.date.accessioned 2019-01-22T09:11:02Z
- dc.date.available 2019-01-22T09:11:02Z
- dc.date.issued 2012
- dc.description.abstract We reformulate a class of non-linear stochastic optimal control problems introduced by Todorov (in Advances in Neural Information Processing Systems, vol. 19, pp. 1369-1376, 2007) as a Kullback-Leibler (KL) minimization problem. As a result, the optimal control computation reduces to an inference computation and approximate inference methods can be applied to efficiently compute approximate optimal controls. We show how this KL control theory contains the path integral control method as a special case. We provide an example of a block stacking task and a multi-agent cooperative game where we demonstrate how approximate inference can be successfully applied to instances that are too complex for exact computation. We discuss the relation of the KL control approach to other inference approaches to control.en
- dc.format.mimetype application/pdf
- dc.identifier.citation Kappen HJ, Gómez V, Opper M. Optimal control as a graphical model inference problem. Mach Learn. 2012 May;87(2):159-82. DOI: 10.1007/s10994-012-5278-7
- dc.identifier.doi http://dx.doi.org/10.1007/s10994-012-5278-7
- dc.identifier.issn 0885-6125
- dc.identifier.uri http://hdl.handle.net/10230/36355
- dc.language.iso eng
- dc.publisher Springer
- dc.relation.ispartof Machine Learning. 2012 May;87(2):159-82.
- dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/s10994-012-5278-7
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.subject.keyword Optimal control
- dc.subject.keyword Uncontrolled dynamics
- dc.subject.keyword Kullback-Leibler divergence
- dc.subject.keyword Graphical model
- dc.subject.keyword Approximate inference
- dc.subject.keyword Cluster variation method
- dc.subject.keyword Belief propagation
- dc.title Optimal control as a graphical model inference problem
- dc.type info:eu-repo/semantics/article
- dc.type.version info:eu-repo/semantics/acceptedVersion