全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于神经元网络的博弈行为研究*

, PP. 21-27

Keywords: 神经元网络,博弈系统,专家决策,心理学决策行为

Full-Text   Cite this paper   Add to My Lib

Abstract:

提出以2个Player组成的一个博弈系统.每个Player代表1个智能体,每个Player的输入是另一个Player的输出,每个Player的行为由神经元网络来描述,按照各自目标函数来调整其权值及给出策略.另外,针对2个Player的博弈,基于心理学理论,首次给出15种博弈行为.用神经元网络来模拟每个Player思维判断,使各种博弈行为更接近于人的行为.通过例子仿真,结果表明提出方法是可行有效的.

References

[1]  Basar T, Srikant R. Network Game with a Large Number of Followers. Journal of Optimization Theory and Applications, 2002, 115(3): 479490
[2]  Fernandez F R, Hinojosa M A, Puerto J. Core Solutions in VectorValued Games. Journal of Optimization Theory and Applications, 2002, 112(2): 331360
[3]  Molina E, Tejada J. Linear Production Games with Committee Control: Limiting Behaviour of the Core. European Journal of Operational Research, 2004, 154(3): 609625
[4]  Wang H, Guo M, Efstathiou J. A GameTheoretical Cooperative Mechanism Design for a TwoEchelon Decentralized Supply Chain. European Journal of Operational Research, 2004, 157(2): 372388
[5]  Dockner E J, Leitmann G. Coordinate Transformations and Derivation of OpenLoop Nash Equilibria. Journal of Optimization Theory and Applications, 2001, 110(1): 115
[6]  Liu Y, Simann M A. Noninferior Nash Strategies for MultiTeam Systems. Journal of Optimization Theory and Applications, 2004, 120(1): 2951
[7]  Souza G C. Product Introduction Decisions in a Duopoly. European Journal of Operational Research, 2004, 152(3): 745757
[8]  Fatima S S, Wooldridge M J, Jennings N R. An AgendaBased Framework for MultiIssue Negotiation. Artificial Intelligence, 2004, 152(1): 145
[9]  Komarova N, Niyogi P. Optimizing the Mutual Intelligibility of Linguistic Agents in a Shared World. Artificial Intelligence, 2004, 154(1/2): 142
[10]  Vincent T L, Goh B S, Teo K L. TrajectoryFollowing Algorithms for MinMax Optimization Problems. Journal of Optimization Theory and Applications, 1992, 75(3): 501519

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133