|
|||||
|
|
| 认知无线网络中基于随机博弈框架的频率分配 | |
| 引用本文： | 刘鑫,阚兴一,王三强.认知无线网络中基于随机博弈框架的频率分配[J].辽宁工程技术大学学报(自然科学版),2011,30(5):778-783. |
| 作者姓名： | 刘鑫 阚兴一 王三强 |
| 作者单位： | 1. 解放军理工大学,通信工程学院,江苏,南京,21007 2. 中国人民解放军,7566部队一大队,广西,桂林,541002 3. 中国人民解放军,65631部队修供基地,辽宁,锦州,121000 |
| 基金项目： | 国家973基金资助项目(2009CB320400) |
| 摘 要： | 为了解决认知无线网络中分布式的动态频率分配问题,采用随机博弈的框架,将认知链路建模成自私理性的智能体,并提出了一种以最大化平均Q函数为目标的多智能体学习算法—MAQ。通过MAQ学习,分布式的智能体可以实现间接的协商而不需要交互Q函数和回报值,因为智能体的决策过程需要考虑其他用户的决策。理论证明了MAQ学习算法的收敛性。仿真结果表明,MAQ算法的吞吐量性能接近中心式的学习算法,但是MAQ只需要较少的信息交互。 |
| 关 键 词： | 随机博弈 MARL 认知无线电 资源分配 强化学习 Q学习 分布式网络 Markov过程 |
Distributed frequency allocation based on stochastic game in cognitive radio networks |
|
| LIU Xin,KAN Xingyi,WANG Sanqiang.Distributed frequency allocation based on stochastic game in cognitive radio networks[J].Journal of Liaoning Technical University (Natural Science Edition),2011,30(5):778-783. | |
| Authors: | LIU Xin KAN Xingyi WANG Sanqiang |
| Institution: | LIU Xin1,KAN Xingyi2,WANG Sanqiang3(1.Institute of Communication Engineering,PLA UST,Nanjing 210007,China,2.NO.75660 Troop,PLA,Guilin 541002,3.Maintenance & Supply Base,NO.65631 Troop,Jinzhou 121000,China) |
| Abstract: | In order to achieve a distributed dynamic frequency allocation in cognitive radio network,a stochastic game framework is adopted.Cognitive links are modeled as selfish and rational agents.A new MARL algorithm,maximizing the average Q function algorithm(MAQ),is proposed in this study.With MAQ,distributed agents can realize an indirect coordination without exchanging their rewards and Q functions.Simulation results show that the learning efficiency of MAQ is close to that of centric learning method,while MAQ ... |
| Keywords: | stochastic game MARL cognitive radio resource allocation reinforcement learning Q learning distributed networks Markov process |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |