Performance of LQ-learning in POMDP Environments
-
- Lee Haeyeon
- Dept. of Elec. & Comm. Eng., School of Eng., Tohoku Univ.
-
- Kamaya Hiroyuki
- Dept. of Elec. Eng., Hachinohe National College of Technology
-
- Abe Kenich
- Dept. of Elec. & Comm. Eng., School of Eng., Tohoku Univ.
説明
In this paper, we propose a new type of LQ-learning to solve POMDP. In the POMDP environment, the agent cannot observe the environment directly. In the LQ-learning, in order to dicriminate partially observed states, the agent attaches label to each observation which perceived as the same ones. Unlike our previous LQ-learning, we make preparations of knowledge about the environment in advance. The knowledge is automatically acquired by Kohenen’s Self-Organizing Map (SOM), which provides the knowledge about state transitions to the agent. Then, LQ-learning agent attaches labels to observations with reference to a map obtained by SOM.
収録刊行物
-
- SICE Annual Conference Program and Abstracts
-
SICE Annual Conference Program and Abstracts 2002 (0), 174-174, 2002
公益社団法人 計測自動制御学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390282680561053568
-
- NII論文ID
- 130006960136
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可
