Dynamic Fuzzy Q-Learning with Facilities of Tuning States and Removing Pairs of State and Actions

DOI 1 Citations 9 References
  • HOSOYA Yu
    Department of Mathematics and Information Sciences, Graduate School of Science, Osaka Prefecture University
  • UMANO Motohide
    Department of Mathematics and Information Sciences, Graduate School of Science, Osaka Prefecture University

Bibliographic Information

Other Title
  • 状態の調整および状態と行動の組の削除機能を持つ動的ファジィQ-learning

Abstract

Fuzzy Q-learning has been studied that can treat a continuous state, since Q-learning treats only a discrete state. Dynamic Fuzzy Q-Learning (DFQL) has been proposed, where a new pair of state and actions is dynamically added to a given initial table of Q value. We propose a more flexible dynamic fuzzy Q-learning with facilities of tuning states of fuzzy sets and removing pairs of state and actions. We tune the center values and widths of fuzzy sets with TD (Temporal Difference) error of V value, which is evaluated value of states. We apply forgetting learning to fuzzy sets and V value and remove unnecessary fuzzy sets and unnecessary pairs of state and actions. We apply the method to the pursuit problem in a continuous environment.

Journal

Citations (1)*help

See more

References(9)*help

See more

Keywords

Details 詳細情報について

  • CRID
    1390282680163908352
  • NII Article ID
    130004705732
  • DOI
    10.3156/jsoft.26.844
  • ISSN
    18817203
    13477986
  • Text Lang
    ja
  • Data Source
    • JaLC
    • Crossref
    • CiNii Articles
  • Abstract License Flag
    Disallowed

Report a problem

Back to top