群体环境下基于随机对策的多Agent局部学习算法  

Local Learning Algorithm for Multi-agent Based on Stochastic Games under Group Environment

作　　者：尹怡欣[1] 江道平[1] 班晓娟[1] 孟祥嵩[1] 

机构地区：[1]北京科技大学信息工程学院,北京100083

出　　处：《信息与控制》2008年第6期703-708,共6页Information and Control

基　　金：国家自然科学基金资助项目(60503024;60374032)

摘　　要：基于群体环境中个体agent局部感知和交互的生物原型,提出一种随机对策框架下的多agent局部学习算法.算法在与局部环境交互中采用贪婪策略最大化自身利益.分别在零和、一般和的单个平衡点和多个平衡点情形下改进了Nash-Q学习算法;提出了行为修正方法,并证明了算法收敛、计算复杂度降低.A local learning algorithm for multi-agent-based stochastic games is proposed in light of the fact that the individual performs local perception and interaction in group. In the algorithm, every agent adopts greedy policy to maximize- its payoff when interacting with the environment. The Nash-Q earning algorithm is improved respectively in situations of zero-sum, general-sum games with only one equilibrium or multi-equilibrium. Besides, the method to modify the behavior is proposed, and it is proved that the algorithm is convergent and the computing complexity is reduced.

关 键 词：多AGENT学习 随机对策 Nash—Q 局部学习 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]