R-learning with Multiple State-action Value Tables
-
- Ishikawa Koichiro
- School of Knowledge Science, Japan Advanced Institute of Science and Technology
-
- Sakurai Akito
- Department of Administration Engineering, Faculty of Science and Technology, Keio University
-
- Fujinami Tsutomu
- School of Knowledge Science, Japan Advanced Institute of Science and Technology
-
- Kunifuji Susumu
- School of Knowledge Science, Japan Advanced Institute of Science and Technology
Bibliographic Information
- Other Title
-
- 複数の状態行動価値表を用いたR学習の高速化
- フクスウ ノ ジョウタイ コウドウ カチヒョウ オ モチイタ R ガクシュウ ノ コウソクカ
Search this article
Abstract
We propose a method to improve the performance of R-learning, a reinforcement learning algorithm, by using multiple state-action value tables. Unlike Q- or Sarsa learning, R-learning learns a policy to maximize undiscounted rewards. Multiple state-action value tables cause substantial explorations as needed and make R-learnings to work well. Efficiency of the proposed method is verified through experiments in simulation environment.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 126 (1), 72-82, 2006
The Institute of Electrical Engineers of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390001204604267008
-
- NII Article ID
- 10016922097
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 7786275
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed