期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

一种基于Q学习的分布式多任务流调度算法 被引量：1

Distributed Scheduling Algorithm for Multiple Task Flows Based on Q-learning
下载PDF
导出
摘要 近来实时动态任务分配机制得到越来越多的研究.考虑多任务流并存时的任务分配问题,提出基于Q学习的分布式多任务流调度算法,不仅能适应自身任务流的到达过程,还充分兼顾其他任务流的到达及分配的影响,从而使得整个系统长期期望回报最大.分布式特性使得算法适用于开放的,局部可见的多Agent系统;强化学习的采用使得任务分配决策自适应系统环境隐藏的不确定性.实验表明此算法具有较高的任务吞吐量和任务完成效率. Recently real-time dynamic task allocation mechanisms draw more attention.Allocation of multiple task flows are considered in this paper,and a distributed scheduling algorithm based on Q-learning for multiple task flows is proposed.This algorithm can not only adapt to task flow on itself,but also take arrival and allocation of other task flows into account,thereby maximizing long-term expected reward of the whole system.Distributed property renders it applicable to open multi-agent systems with local visibility,while reinforcement learning makes allocation decisions adaptable to environment uncertainty.Experiments establish that the algorithm has higher task throughput,improving system efficiency.
作者 肖正 马胜祥 张世永
机构地区 复旦大学计算机科学技术学院
出处 《小型微型计算机系统》 CSCD 北大核心 2010年第4期597-602,共6页 Journal of Chinese Computer Systems
关键词 Agent合作 任务分配 多任务流 Q学习 agent cooperation task allocation multiple task flows Q-learning
分类号 TP393 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献12

  • 1EI-Rewini H,Lewis T G.Scheduling parallel program tasks onto arbitrary target machines[J].Journal of Parallel and Distributed Computing,1990,9(1):138-153.
  • 2Hesham Ali,Hesham EI-Rewini.Task allocation in distributed systems[J].Journal of Combinatorial Mathematics and Combinatorial Computing,1993,14(1):15-32.
  • 3Yoav Shoham,Rob Powers,Troud Grenager.Multi-agent reinforcement learning:a critical survey[R].Technical Report,Stanford University,2003.
  • 4仲宇,顾国昌,张汝波.多智能体系统中的分布式强化学习研究现状[J].控制理论与应用,2003,20(3):317-322. 被引量：11
  • 5Hosam Hanna,Abdel-lllah Mouaddib.Task selection problem under uncertainty as decision-making[C].In:Proc.of International Conference on Autonomous Agent and Multi-Agent System (AAMAS),2002,1303-1308.
  • 6Abdallah Sherief,Lesser Victor.Modeling task allocation using a decision theoretic model[A].In:Proc.of Fourth International Joint Conference on Autonomous Agents and Multi-Agent Systems[C],ACM Press,2005,719-726.
  • 7Abdallah Sherief,Lesser Victor.Learning task allocation via multi-level policy gradient algorithm with dynamic learning rate[C].In:Proceedings of Workshop on Planning and Learning in A Priori Unknown or Dynamic Domains,the International Joint Conference on Artificial Intelligence,IJCAI,2005,76-82.
  • 8Abdallah Sherief,Lesser Victor.Learning the task allocation game[A].In:Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multi-Agent Systems[C],ACM Press,2006,850-857.
  • 9Mailler Roger,Lesser Victor.A cooperative mediation based protocol for dynamic.distributed resource allocation[M].IEEE Transaction on Systems,Man,and Cybernetics,Part C,Special Issue on Game theoretic Analysis and Stochastic Simulation of Negotiation Agents,IEEE Press,2006,36(1):80-91.
  • 10Krainin Michael,An Bo,Lesser Victor.An application of automated negotiation to distributed task allocation[A].IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT 2007)[C],IEEE Computer Society Press,2007,138-145.

二级参考文献57

  • 1SUTTON R. Learning to predict by the methods of temporal difference [J]. Machine Learning, 1988,3( 1 ) :9 - 44.
  • 2RIBEIRO C. Embedding a priori knowledge in reinforcement learning [ J]. J of Intelligent and Robotic Systems, 1998,21 ( 1 ) :51 - 71.
  • 3OH C, NAKASHIMA T, ISHIBUCHI H. Initialization of Q -values by fuzzy rules for accelerating Q -learning [A]. Proc of IEEE Int Conf on Neural Networks [ C ]. Piscataway, NJ: IEEE Press,1998:2051 - 2056.
  • 4ISHIBUCHI H, NAKASHIMA T, MIYAMOTO H. Fuzzy Q-learning for a multi-player non-cooperative repeated game[ A]. Proc of IEEE Int Conf on Fuzzy Systems [ C]. Piscataway,NJ: IEEE Press, 1997:1573 - 1579.
  • 5SUN R, PETERSON T. Multiagent reinforcement learning: weighting and partitioning [J]. Neural Networks, 1999, 12(4) :727 - 753.
  • 6TAKAHASHI Y, ASADA M, HOSODA K. Reasonable performance in less learning time by real robot based on incremental state space segmentation [ A ]. Proc of IEEE/ RSJ Int Conf on Intelligent Robots and Systems [C]. Piscataway, NJ:IEEE Press, 1996:1518.
  • 7HOUGEN D F, GINI M, SLAGLE J. Partitioning input space for reinforcement learning for control [ A ]. Proc of IEEE Int Conf on Neural Networks [C]. Piscataway, NJ: IEEE Press, 1997:755-760.
  • 8FINTON D J, HU Y. An application of importance-based feature extraction in reinforcement learning [ A ]. Proc of the 4th IEEE Workshop on Neural Networks for Signal Processing [ C]. Piscataway,NJ:IEEE Press, 1994:52 - 60.
  • 9ASADA M, NODA S, HOSODA K. Action-based sensor space segmentation for soccer robot learning [J]. Applied Artificial Intelligente, 1998, 12(2/3) : 149 - 164.
  • 10SUN R, PETERSON T. Partitioning in reinforcement learning[ A]. Proc of Int Joint Conf on Neural Networks [ C]. Piscataway,NJ:IEEE Press, 1999:1133- 1138.

共引文献10

同被引文献7

引证文献1

二级引证文献2

小型微型计算机系统
2010年 第4期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部