-
- MARKON Sandor
- Fujitec Research Center, Ltd.
-
- 喜多 一
- 京都大学工学部
-
- 西川 〓一
- 京都大学工学部
書誌事項
- タイトル別名
-
- Adaptive Optimal Elevator Group Control by Use of Neural Networks
- ニューラル ネットワーク オ リヨウシタ テキオウガタ エレベータ グンカンリ
この論文をさがす
説明
The control of a group of elevators is a difficult stochastic control problem, because of the random and unpredictable passenger arrivals. Here we propose a new method for constructing an adaptive controller for stochastic systems, by using a combination of neural networks and an on-line reinforcement learning based on stochastic approximation. This method combines an efficient supervised learning with a general reinforcement adaptation. The supervised learning is used to prepare the controller with domain-specific knowledge, and for initializing it to emulate an existing controller. The reinforcement learning is used for adaptation, with a special attention paid to allow online operation. The new method is used to develop an adaptive, optimal elevator group controller. Results of simulation tests indicate the feasibility of using the proposed method for industrial applications.
収録刊行物
-
- システム制御情報学会論文誌
-
システム制御情報学会論文誌 7 (12), 487-497, 1994
一般社団法人 システム制御情報学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390282680142640512
-
- NII論文ID
- 10007138401
-
- NII書誌ID
- AN1013280X
-
- ISSN
- 2185811X
- 13425668
- http://id.crossref.org/issn/00138444
-
- NDL書誌ID
- 3899546
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可