Reinforcement Learning Based on Dynamic Construction of the Fuzzy State Space - Sharing and Removing Fuzzy Sets of the State

DOI
  • Hosoya Yu
    Department of Mathematics and Information Sciences, Graduate School of Science, Osaka Prefecture Univesity
  • Yamamura Tadayoshi
    Department of Mathematics and Information Sciences, Graduate School of Science, Osaka Prefecture Univesity
  • Umano Motohide
    Department of Mathematics and Information Sciences, Graduate School of Science, Osaka Prefecture Univesity
  • Seta Kazuhisa
    Department of Mathematics and Information Sciences, Graduate School of Science, Osaka Prefecture Univesity

Bibliographic Information

Other Title
  • 強化学習におけるファジィ状態空間の動的構築 - 状態のファジィ集合の共有と削除に関する検討 -

Description

We proposed a method of Q-learning with dynamic construction facility of the fuzzy state space with the real number attributes. We initially have no states and gradually add a new state of fuzzy set for the given attributes. We update Q values with the reward and the fuzzy sets with TD (Temporal Difference) error and we remove unnecessary states. When we add a rule in this method, we generate all the fuzzy sets in each attribute, which may lead to have similar fuzzy sets in a certain attribute. In addition, the states gradually increase when the success ratio keeps to be high. So, we adjust a parameter to decrease the occurrences of addition and remove of fuzzy sets when the success ratio is high. Furthermore, we share fuzzy sets with several rules to prevent similar fuzzy sets. As a result of application of this method to the pursuit problem in a real number environment, we have suppressed the increase of the state in the final stage of learning.

Journal

Keywords

Details 詳細情報について

  • CRID
    1390001205672041344
  • NII Article ID
    130005035228
  • DOI
    10.14864/fss.24.0.198.0
  • Text Lang
    ja
  • Data Source
    • JaLC
    • CiNii Articles
  • Abstract License Flag
    Disallowed

Report a problem

Back to top