Show simple item record

dc.contributor.authorMartínez Martínez, David
dc.contributor.authorAlenyà Ribas, Guillem
dc.contributor.authorTorras, Carme
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2015-05-06T17:39:46Z
dc.date.available2015-05-06T17:39:46Z
dc.date.created2014
dc.date.issued2014
dc.identifier.citationMartínez, D.; Alenyà, G.; Torras, C. Finding safe policies in model-based active learning. A: IROS Machine Learning in Planning and Control of Robot Motion Workshop. "Proceedings of the 2014 IROS Machine Learning in Planning and Control of Robot Motion Worksho". Chicago: 2014, p. 1-6.
dc.identifier.urihttp://hdl.handle.net/2117/27799
dc.description.abstractTask learning in robotics is a time-consuming process, and model-based reinforcement learning algorithms have been proposed to learn with just a small amount of experiences. However, reducing the number of experiences used to learn implies that the algorithm may overlook crucial actions required to get an optimal behavior. For example, a robot may learn simple policies that have a high risk of not reaching the goal because they often fall into dead-ends. We propose a new method that allows the robot to reason about dead-ends and their causes. Analyzing its current model and experiences, the robot will hypothesize the possible causes for the dead-end, and identify the actions that may cause it, marking them as dangerous. Afterwards, whenever a dangerous action is included into a plan which has a high risk of leading to a dead-end, the special action request teacher confirmation will be triggered by the robot to actively confirm with a teacher that the planned risky action should be executed. This method permits learning safer policies with the addition of just a few teacher demonstration requests. Experimental validation of the approach is provided in two different scenarios: a robotic assembly task and a domain from the international planning competition. Our approach gets success ratios very close to 1 in problems where previous approaches had high probabilities of reaching dead-ends
dc.format.extent6 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Robòtica
dc.subject.otherintelligent robots
dc.subject.otherlearning (artificial intelligence)
dc.subject.otherplanning (artificial intelligence)
dc.subject.otheruncertainty handling.
dc.titleFinding safe policies in model-based active learning
dc.typeConference report
dc.contributor.groupUniversitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI
dc.description.peerreviewedPeer Reviewed
dc.subject.inspecClassificació INSPEC::Automation::Robots::Intelligent robots
dc.relation.publisherversionhttp://www.cs.unm.edu/amprg/mlpc14Workshop/proceedings.html
dc.rights.accessOpen Access
drac.iddocument15249644
dc.description.versionPostprint (author’s final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/269959/EU/Intelligent observation and execution of Actions and manipulations/INTELLACT
upcommons.citation.authorMartínez, D.; Alenyà, G.; Torras, C.
upcommons.citation.contributorIROS Machine Learning in Planning and Control of Robot Motion Workshop
upcommons.citation.pubplaceChicago
upcommons.citation.publishedtrue
upcommons.citation.publicationNameProceedings of the 2014 IROS Machine Learning in Planning and Control of Robot Motion Worksho
upcommons.citation.startingPage1
upcommons.citation.endingPage6


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Except where otherwise noted, content on this work is licensed under a Creative Commons license: Attribution-NonCommercial-NoDerivs 3.0 Spain