Task-Oriented Reinforcement Learning for Continuing Task in Dynamic Environment
-
- Kamal Md.Abdus Samad
- Department of Electrical and Electronic Systems Engineering, Graduate School of Information Science and Electrical Engineering, Kyushu University : Graduate Student
-
- Murata Junichi
- Department of Electrical and Electronic Systems Engineering, Faculty of Information Science and Electrical Engineering, Kyushu University
-
- Hirasawa Kotaro
- Graduate School of Information, Production and Systems, Waseda University
Search this article
Abstract
This paper presents task-oriented reinforcement learning, a modified approach of reinforcement-learning to simplify continuing dynamic problems in a more realistic and humanlike way of thinking from the viewpoint of the tasks. In this learning method an agent takes as input the `state of task' instead of 'state of environment' and chooses appropriate action to achieve the goal of the corresponding task. The proposed system learns from the viewpoint of tasks that enables the system to find and follow a precise policy in a continuing-dynamic environment and offers simple implementation for a multiple agents system.
Journal
-
- 九州大学大学院システム情報科学紀要
-
九州大学大学院システム情報科学紀要 9 (1), 7-12, 2004-03-26
Faculty of Information Science and Electrical Engineering, Kyushu University
- Tweet
Details 詳細情報について
-
- CRID
- 1390009224843564672
-
- NII Article ID
- 110000580056
-
- NII Book ID
- AN10569524
-
- DOI
- 10.15017/1515919
-
- ISSN
- 21880891
- 13423819
-
- HANDLE
- 2324/1515919
-
- NDL BIB ID
- 6961230
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- IRDB
- NDL
- CiNii Articles
-
- Abstract License Flag
- Allowed