HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
情報科学研究科  >
雑誌発表論文等  >

Modeling of autonomous problem solving process by dynamic construction of task models in multiple tasks environment

フルテキスト
N.N19-8.pdf265.67 kBPDF見る/開く
この文献へのリンクには次のURLを使用してください:http://hdl.handle.net/2115/16898

タイトル: Modeling of autonomous problem solving process by dynamic construction of task models in multiple tasks environment
著者: Ohigashi, Yu 著作を一覧する
Omori, Takashi 著作を一覧する
キーワード: Model-based reinforcement learning
Multiple tasks
Task model
Reuse of knowledge
発行日: 2006年10月
誌名: Neural Networks
巻: 19
号: 8
開始ページ: 1169
終了ページ: 1180
出版社 DOI: 10.1016/j.neunet.2006.05.037
抄録: Traditional reinforcement learning (RL) supposes a complex but single task to be solved. When a RL agent faces a task similar to a learned one, the agent must relearn the task from the beginning because it doesn’t reuse the past learned results. This is the problem of quick action learning, which is the foundation of decision making in the real world. In this paper, we suppose agents that can solve a set of tasks similar to each other in a multiple tasks environment, where we encounter various problems one after another, and propose a technique of action learning that can quickly solve similar tasks by reusing previously learned knowledge. In our method, a model-based RL uses a task model constructed by combining primitive local predictors for predicting task and environmental dynamics. To evaluate the proposed method, we performed a computer simulation using a simple ping-pong game with variations.
Relation (URI): http://www.sciencedirect.com/science/journal/08936080
資料タイプ: article (author version)
URI: http://hdl.handle.net/2115/16898
出現コレクション:雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

提供者: 大東 優

 

本サイトに関するご意見・お問い合わせは repo at lib.hokudai.ac.jp へお願いします。 - 北海道大学