Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/133994
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | Competitive function approximation for reinforcement learning |
Autor: | Agostini, Alejandro CSIC ORCID; Celaya, Enric CSIC ORCID | Fecha de publicación: | 2014 | Editor: | CSIC-UPC - Instituto de Robótica e Informática Industrial (IRII) | Citación: | IRI-TR-14-05 (2014) | Resumen: | The 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 editor: | http://www.iri.upc.edu/publications/show/1599 | URI: | http://hdl.handle.net/10261/133994 |
Aparece en las colecciones: | (IRII) Informes y documentos de trabajo |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Reinforcement-Learning.pdf | 4,45 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
Page view(s)
194
checked on 24-abr-2024
Download(s)
288
checked on 24-abr-2024
Google ScholarTM
Check
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.