Reinforcement learning in the robocup-soccer keepaway

• Francisco Javier García Polo ; Fernández, Fernando ^[1] ; Veloso, Manuela ^[2]
  1. [1] Universidad Carlos III de Madrid

     Universidad Carlos III de Madrid

     Madrid, España

     
  2. [2] Carnegie Mellon University

     Carnegie Mellon University

     City of Pittsburgh, Estados Unidos

     
• Localización: XII Conferencia de la Asociación Española para la Inteligencia Artificial: (CAEPIA 2007). Actas / coord. por Daniel Borrajo Millán , Luis Castillo Vidal , Juan Manuel Corchado Rodríguez , Vol. 1, 2007, ISBN 978-84-611-8847-5, págs. 357-366
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Many researchers purpose reinforcement learning (RL) as a form of machine learning for robot learning. However, there are several issues that need to be considered when applying (RL) techniques to robot tasks. There are many different (RL) algorithms available such as Q-learning or Sarsa. These algorithms may produce different results. In complex domains with large states and action spaces is necessary to apply generalization techniques such as function approximation. Last, a right balance between exploration and exploitation is required. In this paper we review these issues in order to improve the learning process in the keepaway domain. We present some new combinations in the choice of the RL algorithm, the generalization method and the exploration-exploitation strategy.