English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/127587
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:

Finding safe policies in model-based active learning

AutorMartínez, David ; Alenyà, Guillem ; Torras, Carme
Fecha de publicación2014
CitaciónIROS 2014
ResumenTask learning in robotics is a time-consuming process, and model-based reinforcement learning algorithms have been proposed to learn with just a small amount of experiences. However, reducing the number of experiences used to learn implies that the algorithm may overlook crucial actions required to get an optimal behavior. For example, a robot may learn simple policies that have a high risk of not reaching the goal because they often fall into dead-ends. We propose a new method that allows the robot to reason about dead-ends and their causes. Analyzing its current model and experiences, the robot will hypothesize the possible causes for the dead-end, and identify the actions that may cause it, marking them as dangerous. Afterwards, whenever a dangerous action is included into a plan which has a high risk of leading to a dead-end, the special action request teacher confirmation will be triggered by the robot to actively confirm with a teacher that the planned risky action should be executed. This method permits learning safer policies with the addition of just a few teacher demonstration requests. Experimental validation of the approach is provided in two different scenarios: a robotic assembly task and a domain from the international planning competition. Our approach gets success ratios very close to 1 in problems where previous approaches had high probabilities of reaching dead-ends.
DescripciónTrabajo presentado al IROS: "Machine Learning in Planning and Control of Robot Motion Workshop" (IROS MLPC), celebrado en Chicago, Illinois (US) del 14 al 18 de septiembre.
Este ítem (excepto textos e imágenes no creados por el autor) está sujeto a una licencia de Creative Commons: Attribution-NonCommercial-NoDerivs 3.0 Spain.
Versión del editorhttp://www.cs.unm.edu/amprg/mlpc14Workshop/index.html
Aparece en las colecciones: (IRII) Comunicaciones congresos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
1560-Finding-Safe-Policies.pdf1,71 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.