HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >

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

Files in This Item:
N.N19-8.pdf265.67 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/16898

Title: Modeling of autonomous problem solving process by dynamic construction of task models in multiple tasks environment
Authors: Ohigashi, Yu Browse this author
Omori, Takashi Browse this author
Keywords: Model-based reinforcement learning
Multiple tasks
Task model
Reuse of knowledge
Issue Date: Oct-2006
Journal Title: Neural Networks
Volume: 19
Issue: 8
Start Page: 1169
End Page: 1180
Publisher DOI: 10.1016/j.neunet.2006.05.037
PMID: 16989982
Abstract: 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: http://www.sciencedirect.com/science/journal/08936080
Type: article (author version)
URI: http://hdl.handle.net/2115/16898
Appears in Collections:情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 大東 優

Export metadata:

OAI-PMH ( junii2 , jpcoar_1.0 )

MathJax is now OFF:


 

 - Hokkaido University