• Evolutionary Development of Hierarchical Learning Structures 

      Elfwing, Stefan; Uchibe, Eiji; Doya, Kenji; Christensen, Henrik I. (Georgia Institute of TechnologyInstitute of Electrical and Electronics Engineers, 2007-04)
      Hierarchical reinforcement learning (RL) algorithms can learn a policy faster than standard RL algorithms. However, the applicability of hierarchical RL algorithms is limited by the fact that the task decomposition has ...