dc.creatorPalombarini, Jorge Andrés
dc.creatorMartínez, Ernesto Carlos
dc.date.accessioned2019-02-15T16:48:07Z
dc.date.accessioned2022-10-15T00:58:36Z
dc.date.available2019-02-15T16:48:07Z
dc.date.available2022-10-15T00:58:36Z
dc.date.created2019-02-15T16:48:07Z
dc.date.issued2012-12
dc.identifierPalombarini, Jorge Andrés; Martínez, Ernesto Carlos; Task Rescheduling using Relational Reinforcement Learning; IBERAMIA; Inteligencia Artificial; 50; 12-2012; 57-68
dc.identifier1137-3601
dc.identifierhttp://hdl.handle.net/11336/70276
dc.identifier1988-3064
dc.identifierCONICET Digital
dc.identifierCONICET
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/4327510
dc.description.abstractGenerating and representing knowledge about heuristics for repair-based scheduling is a key issue in any rescheduling strategy to deal with unforeseen events and disturbances. Resorting to a feature-based propositional representation of schedule states is very inefficient and generalization to unseen states is highly unreliable whereas knowledge transfer to similar scheduling domains is difficult. In contrast, first-order relational representations enable the exploitation of the existence of domain objects and relations over these objects, and enable the use of quantification over objectives (goals), action effects and properties of states. In this work, a novel approach which formalizes the re-scheduling problem as a Relational Markov Decision Process integrating first-order (deictic)representations of (abstract) schedule states is presented. Task rescheduling is solved using a relational reinforcement learning algorithm implemented in a real-time prototype system which makes room for an interactive scheduling strategy that successfully handle different repair goals and disruption scenarios. An industrial case study vividly shows how relational abstractions provide compact repair policies with minor computational efforts.
dc.languageeng
dc.publisherIBERAMIA
dc.rightshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectRESCHEDULING
dc.subjectRELATIONAL REINFORCEMENT LEARNING
dc.subjectMANUFACTURING CONTROL
dc.subjectRELATIONAL ABSTRACTIONS
dc.titleTask Rescheduling using Relational Reinforcement Learning
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:ar-repo/semantics/artículo
dc.typeinfo:eu-repo/semantics/publishedVersion


Este ítem pertenece a la siguiente institución