Modular multi-agent reinforcement learning of linked multi-component robotic systems

  1. FERNANDEZ GAUNA, BORJA
Dirigée par:
  1. Manuel Graña Romay Directeur/trice

Université de défendre: Universidad del País Vasco - Euskal Herriko Unibertsitatea

Fecha de defensa: 23 avril 2012

Jury:
  1. Ángel Pascual del Pobil Ferré President
  2. Francisco Xabier Albizuri Irigoyen Secrétaire
  3. Bruno Apolloni-Ghetti Rapporteur
  4. Michal Wozniak Rapporteur
  5. Richard J. Duro Fernández Rapporteur
Département:
  1. Ciencia de la Computación e Inteligencia Artificial

Type: Thèses

Teseo: 115276 DIALNET

Résumé

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.