English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/130283
Share/Impact:
Statistics
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:
Title

Transferring knowledge as heuristics in reinforcement learning: A case-based approach

AuthorsBianchi, Reinaldo; Celiberto, Luiz Antonio; Santos, Paulo Eduardo; Matsuura, Jackson P.; López de Mántaras, Ramón
KeywordsLearning process
Humanoid robot
Empirical evaluations
Case-based approach
2D simulations
Reinforcement learning
Heuristic methods
Meta-algorithms
Case based reasoning
Anthropomorphic robots
Transfer learning
Target domain
Issue Date2015
PublisherElsevier
CitationArtificial Intelligence 226: 102- 121 (2015)
AbstractThe goal of this paper is to propose and analyse a transfer learning meta-algorithm that allows the implementation of distinct methods using heuristics to accelerate a Reinforcement Learning procedure in one domain (the target) that are obtained from another (simpler) domain (the source domain). This meta-algorithm works in three stages: first, it uses a Reinforcement Learning step to learn a task on the source domain, storing the knowledge thus obtained in a case base; second, it does an unsupervised mapping of the source-domain actions to the target-domain actions; and, third, the case base obtained in the first stage is used as heuristics to speed up the learning process in the target domain. A set of empirical evaluations were conducted in two target domains: the 3D mountain car (using a learned case base from a 2D simulation) and stability learning for a humanoid robot in the Robocup 3D Soccer Simulator (that uses knowledge learned from the Acrobot domain). The results attest that our transfer learning algorithm outperforms recent heuristically-accelerated reinforcement learning and transfer learning algorithms. © 2015 Elsevier B.V.
URIhttp://hdl.handle.net/10261/130283
DOI10.1016/j.artint.2015.05.008
Identifiersdoi: 10.1016/j.artint.2015.05.008
issn: 0004-3702
uri: http://www.sciencedirect.com/science/article/pii/S000437021500082X
Appears in Collections:(IIIA) Artículos
(CAB) Artículos
Files in This Item:
File Description SizeFormat 
AI,2015,v226,pp.102-121..pdf705,19 kBAdobe PDFThumbnail
View/Open
Show full item record
Review this work
 

Related articles:


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.