Learning on real robots from experience and simple user feedback
Por favor, use este identificador para citas ou ligazóns a este ítem:
http://hdl.handle.net/10347/17703
Ficheiros no ítem
Metadatos do ítem
Título: | Learning on real robots from experience and simple user feedback |
Autor/a: | Quintía Vidal, Pablo Iglesias Rodríguez, Roberto Rodríguez González, Miguel Ángel Vázquez Regueiro, Carlos |
Centro/Departamento: | Universidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías da Información Universidade de Santiago de Compostela. Departamento de Electrónica e Computación |
Palabras chave: | Autonomous robots | Reinforcement learning | |
Data: | 2013 |
Editor: | Universitat d'Alacant |
Cita bibliográfica: | Quintía Vidal, P., Iglesias Rodríguez, R., Rodríguez González, M., & Vázquez Regueiro, C. (2013). Learning on real robots from experience and simple user feedback. Journal of Physical Agents, 7(1), 57-65. doi:https://doi.org/10.14198/JoPha.2013.7.1.08 |
Resumo: | In this article we describe a novel algorithm that allows fast and continuous learning on a physical robot working in a real environment. The learning process is never stopped and new knowledge gained from robot-environment interactions can be incorporated into the controller at any time. Our algorithm lets a human observer control the reward given to the robot, hence avoiding the burden of defining a reward function. Despite the highly-non-deterministic reinforcement, through the experimental results described in this paper, we will see how the learning processes are never stopped and are able to achieve fast robot adaptation to the diversity of different situations the robot encounters while it is moving in several environments |
Versión do editor: | https://doi.org/10.14198/JoPha.2013.7.1.08 |
URI: | http://hdl.handle.net/10347/17703 |
DOI: | 10.14198/JoPha.2013.7.1.08 |
ISSN: | 1888-0258 |
Dereitos: | This document is under a Creative Commons Attribution license 4.0 International (CC BY 4.0) Atribución 4.0 Internacional |
Coleccións
-
- CiTIUS-Artigos [192]
- EC-Artigos [176]
O ítem ten asociados os seguintes ficheiros de licenza: