Título: Learning on real robots from experience and simple user feedback
Autores: Quintía Vidal, Pablo
Iglesias Rodríguez, Roberto
Rodríguez González, Miguel Ángel
Vázquez Regueiro, Carlos
Fecha: 2013-01-23
2013-01-23
2013-01
Publicador: RUA Docencia
Fuente:
Tipo: info:eu-repo/semantics/article
Tema: Autonomous robots
Reinforcement learning
Ciencia de la Computación e Inteligencia Artificial
Descripción: 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.
This work was supported by the research grant TIN2009-07737 of the Spanish Ministerio de Economía y Competitividad, and María Barbeito program of the Xunta de Galicia.
Idioma: Inglés

Artículos similares:

Choosing the correct paradigm for unknown words in rule-based machine translation systems por Sánchez Cartagena, Víctor Manuel,Esplà Gomis, Miquel,Sánchez Martínez, Felipe,Pérez Ortiz, Juan Antonio
Using external sources of bilingual information for on-the-fly word alignment por Esplà Gomis, Miquel,Sánchez Martínez, Felipe,Forcada Zubizarreta, Mikel L.
10