強化学習における適応的状態空間構成法  [in Japanese] Adaptive State Space Formation Method for Reinforcement Learning  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

For the application of reinforcement learning to real-world problems, an internal state space has to be constructed from a high dimensional observation space. The algorithm presented here constructs the internal state space during the course of learning desirable actions, and assigns local basis functions adaptively depending on the task requirement. The internal state space initially has only one basis function over the entire observation space, and that basis is eventually divided into smaller ones due to the statistical property of locally weighted temporal difference error. The algorithm was applied to an autonomous robot collision avoidance problem, and the validity of the algorithm was evaluated to show, for instance, the need of a smaller number of basis functions in comparison to other method.

Journal

  • The Brain & Neural Networks

    The Brain & Neural Networks 6(3), 144-154, 1999-09-05

    Japanese Neural Network Society

References:  21

Cited by:  6

Codes

  • NII Article ID (NAID)
    10008841609
  • NII NACSIS-CAT ID (NCID)
    AA11658570
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    1340766X
  • Data Source
    CJP  CJPref  J-STAGE 
Page Top