To access the full text documents, please follow this link:

Efficient learning of reactive robot behaviors with a Neural-Q_learning approach
Carreras Pérez, Marc; Ridao Rodríguez, Pere; Batlle i Grabulosa, Joan; Nicosevici, Tudor
The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed
Intel·ligència artificial
Robots mòbils
Xarxes neuronals (Informàtica)
Artificial intelligence
Neural networks (Computer science)
Mobile robots
Tots els drets reservats

Show full item record

Related documents

Other documents of the same author

Carreras Pérez, Marc; Ridao Rodríguez, Pere; García Campos, Rafael; Nicosevici, Tudor
Ridao Rodríguez, Pere; Batlle i Grabulosa, Joan; Ribas Romagós, David; Carreras Pérez, Marc
Ridao Rodríguez, Pere; Batlle i Grabulosa, Joan; Amat i Girbau, Josep; Carreras Pérez, Marc
Carreras Pérez, Marc; Yuh, Junku; Batlle i Grabulosa, Joan; Ridao Rodríguez, Pere