Dynamic Fuzzy Q-Learning with Facilities of Tuning States and Removing Pairs of State and Actions
-
- 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
-
- Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
-
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 26 (5), 844-854, 2014
Japan Society for Fuzzy Theory and Intelligent Informatics
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282680163908352
-
- NII Article ID
- 130004705732
-
- ISSN
- 18817203
- 13477986
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed