Modular multi-agent reinforcement learning of linked multi-component robotic systems
- Manuel Graña Romay Doktorvater
Universität der Verteidigung: Universidad del País Vasco - Euskal Herriko Unibertsitatea
Fecha de defensa: 23 von April von 2012
- Ángel Pascual del Pobil Ferré Präsident/in
- Francisco Xabier Albizuri Irigoyen Sekretär
- Bruno Apolloni-Ghetti Vocal
- Michal Wozniak Vocal
- Richard J. Duro Fernández Vocal
Art: Dissertation
Zusammenfassung
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.