Task Rescheduling using Relational Reinforcement Learning
Fuente:
Redalyc
Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Asociación Española para la Inteligencia Artificial
2012
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1876491252305756160 |
|---|---|
| author | Jorge Palombarini |
| author_facet | Jorge Palombarini |
| contents | Task Rescheduling using Relational Reinforcement Learning Jorge Palombarini Ernesto Martínez Ingeniería Rescheduling Abstract States Manufacturing Systems Relational Reinforcement Learning Relational Markov Decision Process Generating and representing knowledge about heuristics for repair-based scheduling is a keyissue 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 ishighly 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 reinforcementlearning algorithm implemented in a real-time prototype system which makes room for an interactive schedulingstrategy 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. 2012 artículo científico 1137-3601 https://www.redalyc.org/articulo.oa?id=92524944006 en http://www.redalyc.org/revista.oa?id=925 Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial application/pdf Asociación Española para la Inteligencia Artificial Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial (España) Num.50 Vol.15 |
| format | Artículo científico |
| id | redalyc_92524944006 |
| institution | Redalyc |
| language | en |
| publishDate | 2012 |
| publisher | Asociación Española para la Inteligencia Artificial |
| spellingShingle | Task Rescheduling using Relational Reinforcement Learning Jorge Palombarini Ingeniería Rescheduling Abstract States Manufacturing Systems Relational Reinforcement Learning Relational Markov Decision Process Task Rescheduling using Relational Reinforcement Learning Jorge Palombarini Ernesto Martínez Ingeniería Rescheduling Abstract States Manufacturing Systems Relational Reinforcement Learning Relational Markov Decision Process Generating and representing knowledge about heuristics for repair-based scheduling is a keyissue 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 ishighly 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 reinforcementlearning algorithm implemented in a real-time prototype system which makes room for an interactive schedulingstrategy 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. 2012 artículo científico 1137-3601 https://www.redalyc.org/articulo.oa?id=92524944006 en http://www.redalyc.org/revista.oa?id=925 Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial application/pdf Asociación Española para la Inteligencia Artificial Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial (España) Num.50 Vol.15 |
| title | Task Rescheduling using Relational Reinforcement Learning |
| topic | Ingeniería Rescheduling Abstract States Manufacturing Systems Relational Reinforcement Learning Relational Markov Decision Process |
| url | https://www.redalyc.org/articulo.oa?id=92524944006 |