近年來，有許多的協商研究專注於如何使用軟體代理人以應用於電子商務協商和網際網路服務協商領域。本篇研究主要是考慮在仲介代理人收取仲介佣金的前提下，瞭解以往學者所提出的協商架構是否仍能達到公平性。在過去的研究文獻中，並沒有學者去探討這個問題。為了解答這個疑問，因此我們進行了模擬實驗。在模擬中，我們使用軟體代理人執行自動化協商中第三方仲介的角色，而模擬所得的結論就是三方協商架構在仲介代理人收取佣金的情形下，存在漏洞。因此，本篇研究從改善協商架構的角度出發，提出兩個新的協商架構以解決仲介代理人蓄意不公平的問題。經由模擬所提出的新的協商架構，我們證實提出的協商架構，可防止仲介代理人在收取佣金的環境下做出不公正的自利行為。同時，為達成雙向協商的模擬的效果，我們也提出一個在FIPA架構下，改良的雙向協商協定，達到參與協商的雙方皆可提出提案(proposal)之目的。

In recent years, a lot of negotiation literatures pay considerable attention on using software agent to electronic commerce negotiation and web service negotiation applications. The specific aim of the thesis is to investigate the fairness of negotiation architectures proposed in previous research works under the consideration of brokerage commission situation. To answer this question, we conduct experiments by using software agents to simulate automatic service negotiation. Based on our simulation results we found that the mediator (broker agent) of third party negotiation architecture under brokerage commission situation presents biased behavior. To resolve this fairness problem, we present two new negotiation architectures in this thesis. Based on simulation results, the proposed architectures can successfully prevent broker’s biased behavior under the introduction of brokerage commission. In the meanwhile, we also introduce a modified two way negotiation protocol under FIPA agent framework to fulfill basic negotiation requirement by supporting proposal invocation and counter proposal invocation to both negotiating parties.

Chapter 1 Introduction1
1.1 Background and motivation1
1.2 Contribution of the thesis2
1.3 Thesis organization3
Chapter 2 Literature review4
2.1 Negotiation architecture4
2.2 Automated negotiation system5
2.3 Negotiation techniques for agent10
2.4 Negotiation strategy11
2.4.1 Boulware tactic12
2.4.2 Conceder tactic13
2.4.3 Linear tactic14
2.5 Coordination strategy15
2.5.1 Desperate strategy15
2.5.2 Patient strategy16
2.5.3 Optimized patient strategy16
Chapter 3 Unfair pitfall under the third party service negotiation architecture18
3.1 Problem formulation18
3.2 Simulation design20
3.2.1 Normal third party architecture23
3.2.1.1 Patient strategy based on client utility value24
3.2.1.2 Patient strategy based on the sum of client utility value plus provider utility value24
3.2.2 Third party architecture with dishonest mediator25
3.3 Summary of investigation findings26
Chapter 4 Proposed negotiation architectures27
4.1 Design of our architectures27
4.1.1 Dual-mediator architecture29
4.1.2 Three-mediator architecture30
4.2 Decision making model31
4.2.1 Utility function description31
4.2.2 Negotiation proposal making33
4.3 Two-way iterated contract net interaction protocol34
Chapter 5 Simulation evaluation38
5.1 Simulation design38
5.2 Dual-mediator architecture38
5.3 Three-mediator architecture42
5.4 Simulation Findings45
Chapter 6 Conclusion and future work46
Reference47

[1] G. Koua, A. Yekel, T. Sangbong, R.M. Tsamo, Modeling an intelligent e-marketplace software: another outlook of an e-commerce environment, Proceedings of the IEEE International Conference on Signal-Image Technology &. Internet-based Systems (SITIS’05) (2005).
[2] H. Rau, C.W. Chen, W.J. Shiang, and C.J. Lin, Develop an adapted coordination strategy for negotiation in a buyer-driven e-marketplace, Proceedings of the Seventh IEEE International Conference on Machine Learning and Cybernetics, Vol.6, pp.3224-3229 (July 2008).
[3] R.H. Guttman, A.G. Moukas, and P. Maes, Agent-mediated electronic commerce: a survey, Proceedings of Knowledge Engineering Review, Vol.13, No.2, pp.147-159 (July 1998).
[4] P. Maes, R.H. Guttman, A.G. Moukas, Agents That buy and sell, Proceedings of the Communications of the ACM, Vol.42, No.3, pp.81-91 (March 1999).
[5] A. Chavez and P. Maes, Kasbah: An agent marketplace for buying and selling goods, Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi-Agent Technology (PAAM’96), pp.75-90 (April 1996), London, UK.
[6] P.R. Wurman, M.P. Wellman, and W.E. Walsh, The Michigan internet AuctionBot: A configurable auction server for human and software agents, Proceedings of the Second International Conference on Autonomous Agents (Agents’98), pp.301-308 (May 1998), Minneapolis, Minnesota.
[7] R.H. Guttman and P. Maes, Agents-mediated integrative negotiation for retail electronic commerce, Proceedings of the Workshop on Agent Mediated Electronic Trading (AMET’98), pp.70-90 (April 1998), London, UK.
[8] M. Comuzzi and B. Pernici, An architecture for flexible web service QoS negotiation, Proceedings of the Ninth IEEE International Enterprise Distributed Object Computing Conference (EDOC’05), pp.70-82 (Sept 2005).
[9] R.Y.K. Lau, Towards a web services and intelligent agents-based negotiation system for B2B eCommerce, Proceedings of the Electronic Commerce Research and Applications 6, pp.260-273 (2007).
[10] W.Y. Liang, The research of intelligent negotiation agent- application for B2C e-commerce, Proceedings of the International MultiConference of Engineers and Computer Scientists, Vol.1, pp.204-207 (March 2009).
[11] K. Binmore and N. Vulkan, Applying game theory to automated negotiation, Proceedings of the DIMACS Workshop on Economics, Game theory and the Internet (April 1997).
[12] M.J. Wooldridge and N.R. Jennings, Agent theories, architectures, and languages: a survey, Proceedings of the workshop on agent Theories, Architectures and Languages, pp.1-39 (August 1994).
[13] N.R. Jennings, P. Faratin, A.R. Lomuscio, S. Parsons, C. Sierra, and M. Wooldridge, Automated negotiation: prospects, methods and challenges, Proceedings of the International Journal of Group Decision and Negotiation, Vol.10, No.2, pp.199-215 (Mar 2000).
[14] S.H. Wu and V.W. Soo, Game theoretic reasoning in multi-agent coordination by negotiation with a trusted third party, Proceedings of the third annual conference on Autonomous Agents, Seattle, Washington, pp.56-61 (1999).
[15] J.R. Oliver, A machine-learning approach to automated negotiation and prospects for electronic commerce, Proceedings of the Journal of Management Information Systems, Vol. 13, No. 3, pp. 83-112 (Winter 1997).
[16] D. Zeng and K. Sycara, Bayesian learning in negotiation, Proceedings of the International Journal of Human-Computer Studies, Vol.48, No.1, pp.125-141 (January 1998).
[17] P. Faratin, C. Sierra, N.R. Jennings, Negotiation decision functions for autonomous agents, Proceedings of the Journal of Robotics and Autonomous System, Vol.24, No.3-4, pp.159-182 (1998).
[18] R. Schafer, Rules for using multi-attribute utility theory for estimating a user’s interests, Proceedings of the Agent Based Information Systems Workshop, Dortmund, Germany (October 2001).
[19] J.M. Bradshaw (Ed.), Software Agents (1997), AAAI press/MIT press.
[20] F.L. Bellifemine, G. Caire , and D. Greenwood, Developing multi-agent systems with JADE, in Agent Technology (April 2007), Wiley.
[21] M. Calisti, An agent-based approach for coordinated multi-provider service provisioning, in Software Agent Technologies and Autonomic Computing (2003), Whitestein.
[22] Java Agent Development Framework (JADE). URL: <http://jade.tilab.com>
[23] F. Bellifemine, G. Caire, A. Poggi, and G. Rimassa, JADE a White Paper.
URL: <http://jade.tilab.com/papers/2003/WhitePaperJADEEXP.pdf>
[24] F. Bellifemine, G. Caire, T. Trucco, G. Rimassa, JADE Programmer’s Guide.
URL: < http://jade.tilab.com/doc/programmersguide.pdf>
[25] The Foundation for Intelligent Physical Agents. URL:<http://www.fipa.org>