Learning Pedagogical Policies from Few Training Data

Iglesias Maqueda, Ana María; Martínez Fernández, Paloma; Aler, Ricardo; Fernández Rebollo, Fernando

Publication:
Learning Pedagogical Policies from Few Training Data

dc.affiliation.dpto	UC3M. Departamento de Informática	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Computación Evolutiva y Redes Neuronales (EVANNAI)	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Human Language and Accessibility Technologies (HULAT)	es
dc.affiliation.grupoinv	UC3M. Grupo de Investigación: Planificación y Aprendizaje	es
dc.contributor.author	Iglesias Maqueda, Ana María
dc.contributor.author	Martínez Fernández, Paloma
dc.contributor.author	Aler, Ricardo
dc.contributor.author	Fernández Rebollo, Fernando
dc.date.accessioned	2013-09-11T08:29:25Z
dc.date.available	2013-09-11T08:29:25Z
dc.date.issued	2006-08-01
dc.description	[Poster of] 17th European Conference on Artificial Intelligence (ECAI'06). Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds, Riva del Garda, Italy, August 8, 2006
dc.description.abstract	Learning a pedagogical policy in an Adaptive Educational System (AIES) fits as a Reinforcement Learning (RL) problem. However, to learn pedagogical policies requires to acquire a huge amount of experience interacting with the students, so applying RL to the AIES from scratch is infeasible. In this paper we describe RLATES, an AIES that uses RL to learn an accurate pedagogical policy to teach a course of Data Base Design. To reduce the experience required to learn the pedagogical policy, we propose to use an initial value function learned with simulated students, whose model is provided by an expert as a Markov Decision Process. Empirical results demonstrate that the value function learned with the simulated students and transferred to the AIES is a very accurate initial pedagogical policy. The evaluation is based on the interaction of more than 70 Computer Science undergraduate students, and demonstrates that an efficient guide through the contents of the educational system is obtained.
dc.description.sponsorship	This work was supported by the project GPS (TIN2004/07083)
dc.format.extent	6
dc.format.mimetype	application/pdf
dc.identifier.bibliographicCitation	European Conference on Artificial Intelligence (ECAI'06). Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds, [6] p.
dc.identifier.uri	https://hdl.handle.net/10016/17532
dc.identifier.uxxi	CC/0000004167
dc.language.iso	eng
dc.relation.eventdate	August 8, 2006
dc.relation.eventnumber	17
dc.relation.eventplace	Riva de la Garda (Italy)
dc.relation.eventtitle	European Conference on Artificial Intelligence. Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds
dc.rights	Atribución-NoComercial-SinDerivadas 3.0 España
dc.rights.accessRights	open access
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.eciencia	Informática
dc.subject.other	Adaptive and intelligent educational systems
dc.subject.other	Reinforcement learning
dc.title	Learning Pedagogical Policies from Few Training Data
dc.type	conference poster	*
dc.type.hasVersion	AM	*
dspace.entity.type	Publication