藉由網路社會的崛起，代理人技術已漸漸成為資訊科技發展的一個新的方向。在網路上過多的資訊使得代理人的角色變成由單純的資訊擷取、過濾轉變成必須與其它代理人合作，已達到各代理人的自己目標，而又因為各代理人有自己的目標而通常又不願意明白的展現自己的偏好，使得多代理人合作的難度變的更高。而協商方式便成了一種多代理人取得相互協議的方法。
在此論文中，我們有興趣的是在於在代理人雙邊協商的角色中，如何在有限傳遞訊息的限制下達到一個共同的協議。因為時間的限制會迫使代理人讓步，而在讓步的同時間下，如何提出一個能夠更讓對方接受的建議是很重要的，一方面可更快達到最終的共同的協議，一方面也可以增加自己效用收益。在此前提下，我們設計了幾種類型的代理人進行模擬協商的實驗。在實驗結果所提供的證據顯示，當對方的行為模式是具有理性的時候，具有學習功能的代理人是能夠有效的減低傳遞訊息的次數，並且獲得更好的效用收益。而當對方出現不理性的行為時，學習功能並不能為代理人帶來更進一步的收益。

In multi-agent coordination, the bilateral negotiation is an important and essential mechanism for agents to resolve the conflicts and enhance the global performance. However, since agents are usually rational, namely, they are always self-interested and seeking for their maximal expected utility payoff, they will tend to be protecting their own profit and utility during the negotiation. In addition, since the autonomous agents might have to choose the proper concessions and alternatives based on various multi-attribute utility functions during negotiation under bounded number of negotiation messages, it may lead to very inefficient and prolong process before both agents can reach their joint agreement. We assume rational agents are cooperative negotiators under the bounded number of messages. Namely, they are motivated to reach compromised agreement within the time bound in order to get as close to optimal solution as possible. Since agents could observe and learn from other agents’ negotiation proposal, agents could adapt during negotiation in order to speed up the negotiation process. Therefore we incorporate a learning mechanism into agents during the negotiation by using a simple perceptron learning method. We show by experiments that the learning agents can reach their joint agreement much faster than non-learning agents. Besides, the learning agents could reach the joint-agreements that always lie on the Pareto optimal frontier.

[1]. C. Sierra, P. Faratin and N.R. Jennings. A Service-Oreinted Negotiation Model between Autonomous Agents. in Collaboration between Human and Artificial Societies - Coordination and Agent-Based Distributed Computing, Lecture Notes in Artificial Intelligence, Volume 1624, Springer Verlag, pp. 201-220,2000.
[2]. Dajun Zeng and K. Sycara. Benefits of Learning in Negotiation. Stanford Spring Symposium Series on Adaptation, Co-evolution and Learning in Multiagent Systems, AAAI 1996.
[3]. E. Oliveira, J. M. Fonseca, and N. Jennings. Learning to be Competitive in the Market. In Proceedings of the AAAI Workshop on negotiation, July 1999.
[4]. Hyder, Elaine B. and Prietula, Michael J. Getting to Best: Efficiency versus Optimality in Negotiation, Cognitive Science, Volume: 24, Issue: 2, pp. 169-204, April - June 2000.
[5]. Jae-Yeon Kang and Eun-Seok Lee .A Negotiation Model in Electronic Commerce to Reflect Multiple Transaction Factors and Learning. Proceedings of the 13th International Conference on Information Networking, ICOIN 1998.
[6]. K. Sycara. Using Case-Based Reasoning for Plan Adaptation and Repair, Proceedings of the DARPA Case-Based Reasoning Workshop, 1988.
[7]. Mihai Barbuceanu and Wai-Kau Lo. A Multi-Attribute Utility Theoretic Negotiation Architecture for Electronic Commerce. Fourth International Conference on AUTONOMOUS AGENTS, Agents 2000.
[8]. Mor, Y., Goldman, C. V., and Rosenschein, J. S. Learn your Opponent's Strategy (in Polynomial Time). In Proceedings of IJCAI-95 Workshop on Adaptation and Learning in Multiagent Systems, 1995.
[9]. N. R. Jennings, S. Parsons, C. Sierra, and P. Faratin. Automated Negotiation. In Proceedings of the 5th International Conference on Practical Application of Intelligent Agents and Multi-Agent Systems, PAAM-2000.
[10]. N.R. Jennings and J.R Campos. Toward a Social Level Characterization of Socially Responsible Agents. IEEE proceedings on software engineering, 144:pp. 11-25, 1997.
[11]. Osborne, M. J., and Rubinstein. A Course in Game Theory. The MIT Press, 1994.
[12]. P. Faratin, C. Sierra, and N. R. Jennings. Negotiation Decision Functions for Autonomous Agents Int. Journal of Robotics and Autonomous Systems 24 (3-4) pp. 159-182, 1998.
[13]. P. Faratin, C. Sierra, and N. R. Jennings. Using Similarity Criteria to Make Negotiation Trade-Offs. Proceedings of the Fourth International Conference on MultiAgent Systems, ICMAS-2000.
[14]. 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 2nd International Conference on Autonomous Agents 1998.
[15]. Pruitt, D. G. Negotiation Behavior. Academic Press. 1981.
[16]. R. Guttman, A. Moukas, and P. Maes. Agent-Mediated Electronic Commerce: A Survey. Knowledge Engineering Review, 13(2): pp. 147-159, 1998.
[17]. R. Kakehi and Mario Tokoro. A Negotiation Protocol for Conflict Resolution in Multi-Agent Environments. Proceedings of the International Conference on Intelligent and Cooperative Information Systems, pp. 185-196.May 12-14, 1993.
[18]. R.G. Smith and R.Davis. Negotiation as a Metaphor for Distributed Problem Solving Artificial Intelligence 20: pp. 63-109,1983.
[19]. Raiffa, H. The Art and Science of Negotiation. Cambridge, USA, Harvard University Press. 1982.
[20]. Raith, Matthias G. Fair-Negotiation Procedures. Mathematical Social Sciences, 39(3), pp. 303-322, May, 2000.
[21]. Rosenschein, J. and Zlotkin, G.. Rules of Encounter, 1994.
[22]. S. Kraus and D. Lehmann. Designing and Building a Negotiating Automated Agent, Computational Intelligence, 11(1):pp. 132-171, 1995.
[23]. S. Kraus, J. Wilkenfeld and G. Zlotkin Multiagent Negotiation Under Time Constraints, Artificial Intelligence journal, 75(2): pp. 297--345, 1995.
[24]. S. Kraus, K. Sycara, and A. Evenchik. Reaching Agreements through Argumentation: A Logical Model and Implementation. Artificial Intelligence, 1-2(104): pp.1-69, October 1998.
[25]. S. Parsons, C. Sierra and NR Jennings. Agents that Reason and Negotiate by Arguing. Journal of Logic and Computation, 1998.
[26]. T. Sandholm and V.Lesser. Issues in Automated Negotiation and Electronic Commerce. In Proceedings ICMAS 1995.
[27]. T. Sandolm and Nir Vulkan. Bargaining with Deadlines. National Conference on Artificial Intelligence (AAAI). Feb 1,1999.