模糊限制代理人协商
Fuzzy Constraint-Based Agent Negotiation
-
摘要: 随着网际网络的快速发展，信息社会的来临，人们期望能随时随地相互连系、交换讯息以取得所需的信息，造成目前的信息环境具有开放、巨大、及异质的特性。而具有自发性、敏捷性、及社交性之软件代理人(Software Agent)正好适用于此环境，能处理这些问题，因此而成为一重要的研究领域。此外，世界可视为一个多重代理人的环境，人和人之间可能有冲突而需要相互考量，于是协商机制(Negotiation Mechanism)成为代理人相关研究的主要课题之一。代理人协商系两个或多个软件代理人间，经由不断重复的共同决策过程，达成相互可接受之决策目标。然而目前软件代理人大多为特定应用而发展，对于彼此间的合作和竞争等社交性之相关应用，缺乏解决方法之完整架构，造成无法有效地处理代理人群体间沟通协调等问题。因此，本论文系藉由模糊限制处理为基础，来建构多边多议题之协商模式，以获得完整的解题架构。本论文视软件代理人协商为分布式模糊限制问题，以此方式，模糊限制不但能定义具有人类思考观念的代理人需求，并且可以用来表示代理人之间的相互关系。协商策略是代理人用来评估和产生方案，以得到对他们最有利的协议，代理人依照他们自己的协商策略，在整个协商过程中，轮流提案。本论文提出以模糊限制方式为基础之让步策略及交换策略，分别以放松需求及评估既存可替代方案的方式来找到共同一致的协议。这种具有逐渐放松及限制之本质的方式，提供一个有系统的方法，在最高可能满意度的限制条件下，达成对所有代理人都有益的协议。同时因为其搜寻方案着重在对手可能接受的范围，因此这个方法可让代理人更快地接近可接受的协议。而藉由让步及交换策略所产生之不同组合，宏协商策略亦被进一步发展，应用于不同之场景。最后，本论文以旅游规划之协商，来验证所提模式于多边多议题协商中之实用性及有效性，包括：在顾客及旅行社代理人之协商，来阐述所提模式于不同协商策略的协商过程，以及在旅行社、航空公司和旅馆业代理人之协商，来展现所提模式于多边多议题之产生的结果与效力。Abstract: Conflicts between two or more parties arise forvarious reasons and perspectives. Thus, resolution of conflicts frequentlyrelies on some form of negotiation. This paper presents a generalproblem-solving framework for modeling multi-issue multilateral negotiationusing fuzzy constraints. Agent negotiation isformulated as a distributed fuzzy constraint satisfaction problem (DFCSP).Fuzzy constrains are thus used to naturally represent each agent's desiresinvolving imprecision and human conceptualization, particularly when lexicalimprecision and subjective matters are concerned. On the other hand, based onfuzzy constraint-based problem-solving, our approach enables an agent not onlyto systematically relax fuzzy constraints to generate a proposal, but also toemploy fuzzy similarity to select the alternative that is subject to itsacceptability by the opponents. This task of problem-solving is to reach anagreement that benefits all agents with a high satisfaction degree of fuzzyconstraints, and move towards the deal more quickly since their search focusesonly on the feasible solution space. An application to multilateralnegotiation of a travel planning is provided to demonstrate the usefulness andeffectiveness of our framework.
-
-
[1] Bradshaw Jeffrey M. Software Agents. AAAI/The MIT Press, 1997.
[2] Huhns Michnel N, Munindar P Singh (eds.).Readings in Agents. San Francisco, California: Morgan KaufmannPublishers, Inc., 1998.
[3] Pruitt D G. Negotiation Behavior. Academic Press, New York, 1981.
[4] Kersten Gregory E, Gordon Lo. Negotiation support systems andsoftware agents in e-business negotiations. In The FirstInternational Conference on Electronic Business, Hong Kong,December, 2001, pp.19--21.
[5] Rosenschein J S, Zlotkin G.Rules of Encounter: Designing Conventions for Automated Negotiation AmongComputers. Cambridge, Massachusetts: MIT Press, 1994.
[6] Ren Z, Anumba C J, Ugwu O O. Negotiation in a multi-agentsystem for construction claims negotiation. Applied ArtificialIntelligence, 2002, 16: 359--394.
[7] Oliver Jim R. On artificial agents fornegotiation in electronic commerce. In Proc. The 29th AnnualHawaii International Conference on System Sciences, 1996, pp.337--346.
[8] Eaton P S, Freuder E C, Wallace R J. Constraints and agents:Confronting Ignorance. AI Magazine, 1998, 19(2): 51--65.
[9] Zeng D, Sycara K. Bayesian learning in negotiation. Internat. J. Human-Computer Stud., 1998, 48(1): 125--141.
[10] Choi Samuel P M, Liu Jiming, Chan Sheung-Ping. A geneticagent-based negotiation system. Computer Networks, 2001, 37:195--204.
[11] Sycara K. Multi-agent compromise vianegotiation. In -Distributed Artificial Intelligence, Vol. 2.Gasser L, Huhns M (eds.), Morgan Kaufmann, San Mateo, CA, 1989, pp.119--139.
[12] Sathi A, Fox M. Constraint-directed negotiation of resourcereallocation. In Distributed Artificial Intelligence,Vol. 2. Gasser L, Huhns M (eds.), Morgan Kaufmann, San Mateo, CA, 1989,pp.163--195.
[13] Matos Noyda, Carles Sierra. Evolutionary computing andnegotiating agents. Agent Mediated ElectronicCommerce, AMET-98, In Lecture Notes in Artificial Intelligent 1571, 1998, pp.126--150.
[14] Barbuceanu M, Lo W-K. A multi-attribute utility theoreticnegotiation architecture for electronic commerce. In Proc.the Fourth International Conference on Autonomous Agents, 2000,pp.239--246.
[15] Luo Xudong, Nicholas R Jennings, Nigel Shadbolt et al. A fuzzy constraint based model forbilateral multi-issue negotiations in semi-competitive environments. Artificial Intelligence, 2003, 148: 53--102.
[16] Kowalczyk R, Bui V. FeNAs: A fuzzy e-negotiation agentssystem. In Proc. The IEEE/IAFE/INFORMS 2000 Conference onComputational Intelligence (CIFEr 2000), New York, 2000, pp.26--29.
[17] Faratin P, Sierra C, Jennings N R.Using similarity criteria to make trade-offs in automated negotiation. Artificial Intelligence, 2002, 142(2): 205--237.
[18] Zadeh L A. Fuzzy sets as a basis for atheory of possibility. Fuzzy Sets and Systems, 1978, 1: 3--28.
[19] Lai R. Fuzzy constraint processing
[Dissertation].NCSU, Raleigh, N. C., 1992.[20] Dubois D, Fragier H, Prade H. Propagation and satisfaction offlexible constraints. In -Fuzzy Sets, Neural Networks and SoftComputing, Van Nostrand Reinhold, Yager R, Zadeh L (eds.), New York,1994, pp.166--187.
[21] Bowen J, Lai R, Bahler D. Lexical imprecision in fuzzyconstraint networks. In Proc. AAAI-92, San Jose, CA, 1992,pp.616--621.
[22] Saaty T L. The Analytic Hierarchy Process. McGraw-Hill, NewYork, 1980.
[23] Yager R R, Filev D P. Essential of Fuzzy Modeling andControl. John Wiley & Sons, New York, 1994.
[24] Liu X. Entropy, distance measure and similarity measure offuzzy sets and their relations. Fuzzy Sets and Systems, 1992, 52:305--318.
[25] Finin T, McKay D, McEntire R. KQML---A language and protocolfor knowledge and information exchange. Technical Report CS-94-02,Computer Science Department, University of Maryland, UMBC, Baltimore MD21228, 1994.
[26] Searle J. Speech Acts. Cambridge University Press, 1969.
[27] Bellman R E, Zadeh L A. Decision making in a fuzzyenvironment. Management Science, 1970, 17: 141--164.
计量
- 文章访问数: 21
- HTML全文浏览量: 0
- PDF下载量: 1361
下载:
