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

• Autores: Borja Fernández Gauna
• Directores de la Tesis: Manuel Graña Romay (dir. tes.)
• Lectura: En la Universidad del País Vasco - Euskal Herriko Unibertsitatea ( España ) en 2012
• Idioma: inglés
• Tribunal Calificador de la Tesis: Ángel Pascual del Pobil y Ferré (presid.), Francisco Xabier Albizuri Irigoyen (secret.), Michal Wozniak (voc.), Richard J. Duro Fernández (voc.), Bruno Apolloni-Ghetti (voc.)
• Materias:
  • Matemáticas
    • Ciencia de los ordenadores
      • Inteligencia artificial
      • Simulación
• Texto completo no disponible (Saber más ...)
• Resumen

  • 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.