Show simple item record

dc.contributor.authorJacob, D.
dc.contributor.authorPolani, D.
dc.contributor.authorNehaniv, C.L.
dc.date.accessioned2011-11-22T09:01:10Z
dc.date.available2011-11-22T09:01:10Z
dc.date.issued2005
dc.identifier.citationJacob , D , Polani , D & Nehaniv , C L 2005 , Legs that can walk: Embodiment-Based Modular Reinforcement Learning applied . in Procs 2005 IEEE Int Symposium on Computational Intelligence in Robotics and Automation : CIRA 2005 . Institute of Electrical and Electronics Engineers (IEEE) , pp. 365-372 , 2005 IEEE Int Symposium of Computational Intelligence in Robotics & Automation , Espoo , Finland , 27/06/05 .
dc.identifier.citationconference
dc.identifier.isbn0-7803-9355-4
dc.identifier.otherdspace: 2299/932
dc.identifier.otherORCID: /0000-0002-3233-5847/work/86098131
dc.identifier.urihttp://hdl.handle.net/2299/7065
dc.description.abstractExperiments to illustrate a novel methodology for reinforcement learning in embodied physical agents are described. A simulated legged robot is decomposed into structurebased modules following the authors' EMBER principles of local sensing, action and learning. The legs are individually trained to 'walk' in isolation, and re-attached to the robot; walking is then sufficiently stable that learning in situ can continue. The experiments demonstrate the benefits of the modular decomposition: state-space factorisation leads to faster learning, in this case to the extent that an otherwise intractable problem becomes learnable.en
dc.format.extent4797286
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartofProcs 2005 IEEE Int Symposium on Computational Intelligence in Robotics and Automation
dc.titleLegs that can walk: Embodiment-Based Modular Reinforcement Learning applieden
dc.contributor.institutionSchool of Computer Science
dc.contributor.institutionCentre for Computer Science and Informatics Research
dc.contributor.institutionDepartment of Computer Science
dc.contributor.institutionAdaptive Systems
dc.contributor.institutionSchool of Physics, Engineering & Computer Science
dc.contributor.institutionCentre for Future Societies Research
dc.contributor.institutionScience & Technology Research Institute
rioxxterms.typeOther
herts.preservation.rarelyaccessedtrue


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record