Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/29985
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | Rho-learning: a robotics oriented reinforcement learning algorithm |
Autor: | Porta, Josep M. CSIC ORCID | Palabras clave: | Reinforcement learning Robot learning Sensor relevance Walking robots Automation Robots |
Fecha de publicación: | 2000 | Citación: | Technical Report IRI-DT-00-03, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2000. | Resumen: | We present a new reinforcement learning system more suitable to be used in robotics than existing ones. Existing reinforcement learning algorithms are not specifically tailored for robotics and so they do not take advantage of the robotic perception characteristics as well as of the expected complexity of the task that robots are likely to face. In a robot, the information about the environment comes from a set of qualitatively different sensors and in the main par of tasks small subsets of these sensors provide enough information to correctly predict the effect of actions. Departing from this analysis, we outline a new reinforcement learning system that aims at determining relevant subsets of sensors for each action and we present an algorithm that partially implements this new reinforcement learning architecture. Results of the application of the algorithm to the problem of learning to walk with a six legged robot are presented and compared with a well known reinforcement learning algorithm (Q-learning) showing the advantages of our approach. | URI: | http://hdl.handle.net/10261/29985 |
Aparece en las colecciones: | (IRII) Informes y documentos de trabajo |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
doc1.pdf | 314,07 kB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
Page view(s)
253
checked on 23-abr-2024
Download(s)
134
checked on 23-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.