计算机科学 ›› 2017, Vol. 44 ›› Issue (1): 53-59.doi: 10.11896/j.issn.1002-137X.2017.01.010

• 2016第六届中国数据挖掘会议 • 上一篇    下一篇

基于中介Agent的强化学习优化协商模型

张京敏,董红斌   

  1. 哈尔滨工程大学计算机科学与技术学院 哈尔滨150001,哈尔滨工程大学计算机科学与技术学院 哈尔滨150001
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受国家自然科学基金项目(61472095,6),智能教育与信息工程黑龙江省高校重点实验室资助

Optimized Negotiation Model Based on Reinforcement Learning of Medium Agent

ZHANG Jing-min and DONG Hong-bin   

  • Online:2018-11-13 Published:2018-11-13

摘要: 提出了一种基于强化学习的双边优化协商模型。引入了一个中介Agent。在强化学习策略中使用不同的参数产生提议,进而选出最好的参数进行协商。为了进一步提高协商的性能,还提出了基于中介Agent自适应的学习能力。仿真实验结果证明了所提协商方法的有效性,且该方法提高了协商的性能。

关键词: 多Agent,强化学习,自适应学习,中介Agent

Abstract: This paper proposed reinforcement learning bilateral optimized negotiation model based on reinforcement learning.The medium agent was introduced.It uses different parameters in the reinforcement learning strategy to produce proposals,and selects the best parameters to negotiate.The purpose is to further improve the performance of negotiation,and then the article presented the learning ability of adaptive based on medium agent.The simulation results show the effectiveness of the proposed method of negotiation and that it can improve the performance of negotiation.

Key words: Multi-agent system,Reinforcement learning,Adaptive learning,Medium agent

[1] BAARLAG T,HENDRIKX M J C,HINDRIKS K V,et al.Learning about the opponent in automated bilateral negotiation:a comprehensive survey of opponent modeling techniques[J].Autonomous Agents and Multi-Agent Systems,2015,30(5):849-898.
[2] ILANY L,GAL Y.Algorithm selection in bilateral negotiation[J].Autonomous Agents and Multi-Agent Systems,2016,30(4):697-723.
[3] ZHANG X S,KLEIN M,MARSAMAESTRE I.Scalable Complex Contract Negotiation with Structured Search and Agenda Management[C]∥AAAI Conference on Artificial Intelligence.2014.
[4] ZHANG Hua-xiang,HUANG Shang-teng.Agent NegotiationModel Based on Reinforcement learning[J].Computer Enginee-ring,2004,30(10):137-139.(in Chinese) 张化祥,黄上腾.基于增强学习的代理谈判模型[J].计算机工程,2004,30(10):137-139.
[5] SUN T H,CHEN F,ZHU Q S.Reinforcement learning negotiation strategy based on Bayesian classification[J].Chinese Journal of Computer Science,2011,38(9):227-229.(in Chinese) 孙天昊,陈飞,朱庆生.基于贝叶斯分类的增强学习协商策略[J].计算机科学,2011,38(9):227-229.
[6] ZHANG Lin-lan,SONG Hai-gang,CHEN Xue-guang,et al.Asimultaneous multi-issue negotiation through autonomous agents[J].European Journal of Operational Research,2010,210(1):95-105.
[7] SUN Tian-hao,DENG Jun-kun,CAO Feng,et al.Reinforcement Learning Negotiation Strategy based on Opponent Classification[C]∥The International Conference on Computer Science and Service System (CSSS 2011).Nanjing,China,2011:3987-3989.
[8] SUI Xin,CAI Guo-yong,SHI Lei.Multi-agent negotiation strategy and algorithm based on Q-Learning[J].Chinese Journal of computer engineering,2010,36(17):198-200.(in Chinese) 隋新,蔡国永,史磊.基于Q-强化学习的多Agent协商策略及算法[J].计算机工程,2010,36(17):198-200.
[9] CHEN Li-hong,DONG Hong-bin,HAN Qi-long,et al.Bilateral Multi-issue Parallel Negotiation Model Based on Reinforcement Learning[C]∥The 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2013,LNCS 8206).2013.
[10] DIAMAH A,MOHAMMADIAN M,BALACHANDRAN B.Fuzzy utility and inference system for bilateral negotiation[C]∥2012 International Conference on Uncertainty Reasoning and Knowledge Engineering.2012:115-118.
[11] CHEN Li-hong,DONG Hong-bin,ZHOU Yang.A reinforce-ment learning optimized negotiation method based on mediator agent[J].Expert Systems with Applications,2014(41):7630-7640.
[12] 普尔.人工智能:计算Agent基础[M].董红斌,等译,北京:机械工业出版社,2015.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!