基于R学习的合同网实时调度模型  

Real-time contract-net-protocol scheduling model based on R-learning

作　　者：赵良辉[1] 熊作贞 

机构地区：[1]五邑大学经济管理学院,广东江门529020

出　　处：《计算机工程与应用》2014年第10期221-226,237,共7页Computer Engineering and Applications

基　　金：广东省自然科学基金资助项目(No.8452902001001552)

摘　　要：提出一种融入合同网运行机制的R学习方法,以此方法为核心构造Agent形成具有学习能力的实时调度模型。模型以最小化作业累计平均流动比为主要目标,同时借助对强化学习报酬的设计减小机器负载的不均衡性,实现对调度过程的双重优化;构造实时调度实例投入测试的结果证明了模型的绩效。另外,一个包含强化学习Agent与无学习Agent的混合机器环境被构建并测试其性能,测试结果表明:在Agent之间借助强化学习过程形成了某种隐性的合作,正是这种合作保证了高质量实时调度方案的输出。This paper proposes a real-time scheduling model based on contract net protocol structure employing reinforcement learning agents. To this end, an R-learning procedure is elaborated and embedded in machine agents’decision process, enabling them to treat bid-invitations in more complicated way than in a simple contract net protocol environment. Efficiency of the proposed method is verified through experiments in a simulated real-time scheduling environment. Furthermore, the performance of mixed machine groups which comprises both reinforcement learning agents and non-reinforcement-learning agents shows that there is spontaneous implicit teamwork occurring between reinforcement learning agents, and this teamwork guarantees high quality output of the scheduling model.

关 键 词：R学习 合同网 多AGENT合作 实时调度 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]