English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/133994
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:

Competitive function approximation for reinforcement learning

AutorAgostini, Alejandro ; Celaya, Enric
Fecha de publicación2014
EditorCSIC-UPC - Instituto de Robótica e Informática Industrial (IRII)
CitaciónIRI-TR-14-05 (2014)
ResumenThe application of reinforcement learning to problems with continuous domains requires representing the value function by means of function approximation. We identify two aspects of reinforcement learning that make the function approximation process hard: non-stationarity of the target function and biased sampling. Non-stationarity is the result of the bootstrapping nature of dynamic programming where the value function is estimated using its current approximation. Biased sampling occurs when some regions of the state space are visited too often, causing a reiterated updating with similar values which fade out the occasional updates of infrequently sampled regions. We propose a competitive approach for function approximation where many different local approximators are available at a given input and the one with expectedly best approximation is selected by means of a relevance function. The local nature of the approximators allows their fast adaptation to non-stationary changes and mitigates the biased sampling problem. The coexistence of multiple approximators updated and tried in parallel permits obtaining a good estimation much faster than would be possible with a single approximator. Experiments in different benchmark problems show that the competitive strategy provides a faster and more stable learning than non-competitive approaches.
Versión del editorhttp://www.iri.upc.edu/publications/show/1599
Aparece en las colecciones: (IRII) Informes y documentos de trabajo
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
Reinforcement-Learning.pdf4,45 MBAdobe PDFVista previa
Mostrar el registro completo

NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.