Constructing an intelligent behavior avatar in a virtual world: a self-learning model based on reinforcement

doi:10.1109/IRI-05.2005.1506510

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 會議論文 > Item 987654321/37594

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/37594

题名:	Constructing an intelligent behavior avatar in a virtual world: a self-learning model based on reinforcement
作者:	Chen, Jui-fa;Lin, Wei-chuan;Bai, Hua-sheng;Yang, Chia-che;Chao, Hsiao-chuan
贡献者:	淡江大學資訊工程學系
日期:	2005-08
上传时间:	2010-04-15 10:21:11 (UTC+8)
出版者:	Institute of electrical and electronics engineers (IEEE)
摘要:	In this paper, a novel method for personal intelligent behavior avatar (IBA) is proposed to acquire autonomous behavior based on the interactions between user and smart objects in the virtual environment. In this method, the behavior decision model and the self-learning model are integrated by Bayesian networks and reinforcement learning. The Bayesian networks can treat interaction experiences using statistical processes, and the sureness of decision making is represented by certainty factors using stochastic reasoning. The reinforcement learning is implemented by learning experimentation or trial and error mechanisms to improve the performance of IBA through feedback. Therefore, the IBA makes a strategic decision that is approximated and appropriate to the user through the self-learning process by reinforcement learning. Finally, the feasibility of this method is investigated by imitating user's behavior and the results of self-learning process. The results of simulation show that the method is successful in imitating user's behavior and improving the performance of IBA.
關聯:	Information Reuse and Integration, Conf, 2005. IRI -2005 IEEE International Conference on, pp.421-426
DOI:	10.1109/IRI-05.2005.1506510
显示于类别:	[資訊工程學系暨研究所] 會議論文

文件中的档案:

档案	描述	大小	格式	浏览次数
0780390938_p421-426.pdf		375Kb	Adobe PDF	717	检视/开启
index.html		0Kb	HTML	236	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....