{ "dc.contributor.author": "Carreras Pérez, Marc" , "dc.contributor.author": "Ridao Rodríguez, Pere" , "dc.contributor.author": "El-Fakdi Sencianes, Andrés" , "dc.date.accessioned": "2010-05-05T12:32:49Z" , "dc.date.available": "2010-05-03T15:06:30Z" , "dc.date.available": "2010-05-05T12:32:49Z" , "dc.date.issued": "2003" , "dc.identifier.citation": "Carreras, M., Ridao, P., i El-Fakdi, A. (2003). Semi-online neural-Q_leaming for real-time robot learning. IEEE/RSJ International Conference on Intelligent Robots and Systems : IROS 2003 : Proceedings, 1, 662-667. Recuperat 05 abril 2010, a http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1250705" , "dc.identifier.isbn": "0-7803-7860-1" , "dc.identifier.uri": "http://hdl.handle.net/10256/2167" , "dc.description.abstract": "Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior" , "dc.format.mimetype": "application/pdf" , "dc.language.iso": "eng" , "dc.publisher": "IEEE" , "dc.relation.isformatof": "Reproducció digital del document publicat a: http://dx.doi.org/10.1109/IROS.2003.1250705" , "dc.relation.ispartof": "© IEEE/RSJ International Conference on Intelligent Robots and Systems : IROS 2003 : Proceedings, 2003, vol. 1, p. 662-667" , "dc.relation.ispartofseries": "Articles publicats (D-ATC)" , "dc.rights": "Tots els drets reservats" , "dc.subject": "Aprenentatge per reforç" , "dc.subject": "Aprenentatge automàtic" , "dc.subject": "Robots" , "dc.subject": "Machine learning" , "dc.subject": "Reinforcement learning" , "dc.title": "Semi-online neural-Q_leaming for real-time robot learning" , "dc.type": "info:eu-repo/semantics/article" , "dc.rights.accessRights": "info:eu-repo/semantics/openAccess" , "dc.identifier.doi": "http://dx.doi.org/10.1109/IROS.2003.1250705" }