Modular multi-agent reinforcement learning of linked multi-component robotic systems
- Manuel Graña Romay Director
Universidade de defensa: Universidad del País Vasco - Euskal Herriko Unibertsitatea
Fecha de defensa: 23 de abril de 2012
- Ángel Pascual del Pobil Ferré Presidente/a
- Francisco Xabier Albizuri Irigoyen Secretario
- Bruno Apolloni-Ghetti Vogal
- Michal Wozniak Vogal
- Richard J. Duro Fernández Vogal
Tipo: Tese
Resumo
THE CONTENTS OF THIS THESIS CAN BE SUMMARIZED AS TWO MAIN IDEAS: MODULAR TECHNIQUES TO DECOMPOSE A REINFORCEMENT LEARNING TASK IN OVER-CONSTRAINED ENVIRONMENTS SUCH AS LINKED-MCRS AS SEVERAL CONCURRENT SUB-TASKS, AND EXTENSION OF THESE MODULAR REINFORCEMENT LEARNING APPROACHES TO MULTI-AGENT REINFORCEMENT LEARNING ENVIRONMENTS.