Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/30274
COMPARTIR / EXPORTAR:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Invitar a revisión por pares abierta
Título

Applying categorization to improve learning in complex environments

AutorAgostini, Alejandro CSIC ORCID; Celaya, Enric CSIC ORCID
Palabras claveReinforcement learning
Categorization
Complex environments
Cybernetics: Artificial intelligence: Generalisation (artificial intelligence)
Automation: Robots: Intelligent robots
Cybernetics: Artificial intelligence: Learning (artificial intelligence)
Machine learning
Intelligent robots and autonomous agents
Automatic theorem proving
Fecha de publicación2004
EditorUniversidad Politécnica de Cataluña
Citación1a Jornada de Recerca en Automàtica, Visió i Robòtica: 263-268 (2004)
ResumenAn autonomous agent is considered intelligent if it is capable to improve its performance through time, learning by experience. The problem of learning to improve performance from experience has been formalized in the field of Reinforcement Learning. The main difficulty found in this field is that the number of experiences required for learning to take place could be very large depending on the environment structure. If the environment has no structure at all the learning cannot be completed until all actions have been executed at least once in each possible state. Then, the application of reinforcement learning techniques is only fea-sible when the environment presents enough regularity to allow some kind of generalization. Many reinforcement learning techniques have been proposed using different forms of generalization. Despite the diversity of strategies proposed, usual generalization techniques do not take ad-vantage of all the opportunities of generalization. A new algorithm was proposed that exploits a type of regularity that is denoted as categorizability. Categorizability means that from all the relevant features that must be taken into account to decide the best action in any situation, only a few of them are actually relevant in each particular situation. In this paper the categorization and learning capabilities of the algorithm are evaluated using a problem that satisfies to a good extent the categorization property. The categorization achieved is analyzed in detail and illustrated with examples. The algorithm learning performance is compared with those of other learning algorithms. Some improvements of the original algorithm are introduced.
DescripciónJornada de Recerca en Automàtica, Visió i Robòtica (AVR), 2004, Barcelona (España)
URIhttp://hdl.handle.net/10261/30274
ISBN8476538448
Aparece en las colecciones: (IRII) Comunicaciones congresos




Ficheros en este ítem:
Fichero Descripción Tamaño Formato
doc1.pdf250,99 kBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro completo

CORE Recommender

Page view(s)

300
checked on 28-mar-2024

Download(s)

107
checked on 28-mar-2024

Google ScholarTM

Check

Altmetric


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