藉由網際網路提供的方便性, 人們可以經由連結上網路來得到快速交換資訊的利益而不需受到地理上的限制. 許多正在出現的應用也提供了網際網路更多的可能性與遠景. 一個特別的主題, 有關於智慧型代理人如何代表他的客戶自動地完成任務, 近來已在人工智慧研究及電子商務的領域中引起許多注意.
我們有興趣的主題在於, 如何設計一個交易代理人, 使其可以在電子市場中自動的交易並且反映出客戶的喜好. 我們使用一種同步化雙邊拍賣機制作為模擬的測試平台, 並設計一個具有增強式學習能力的代理人來完成此一任務. 我們做了一系列的實驗, 並以不同的設定來檢視我們所設計的具有學習能力之代理人的表現. 藉由我們的實驗結果所提供的證據顯示, 當他的對手有著同樣的行為與一致的策略時, 代理人可以藉由學習得到利益, 但是當市場上充滿著不同類型的代理人伴隨著多樣性的行為時, 學習並無法為代理人帶來更進一步的利益.

With facilities provided by Internet, people who connect to it could benefit from rapid information exchange without geographical limitation. And many applications are emerging to provide Internet with more possibilities and visions. A special topic about how intelligent agents represent customers to automatically accomplish tasks has recently attracted a lot of attentions both in the field of artificial intelligence research, and electronic commerce.
The topic, which we are interested in, is how to design a trading agent that automatically trades in electronic markets and reveals preferences of customers. We use a synchronous double auction as a simulating test-bed, and design a reinforcement learning agent to accomplish the task. And we conduct a series of experiments with different settings to investigate the performance of our learning agents. As the evidence provided by our experimental results, we show that agents could benefit from learning when the opponent that they are against with has homogeneous behavior and unified strategy, but fail to get further benefits when the market is full of heterogeneous agents with diverse behaviors.

[1]. David Cliff and Janet Bruten. Zero is Not Enough: On The Lower Limit of Agent Intelligence for Continuous Double auction markets. HP Labs technical report HPL-97-141, Hewlett Packard Research Laboratories, Bristol England, 1997.
[2]. Daniel Friedman and John Rust. The Double Auction Market: Institutions, Theories and Evidence. Addison-Wesley, 1993.
[3]. Daniel Friedman. The Double Auction Market Institution: A Survey. In [2] , pp.3-25.
[4]. John H. Gagel and Alvin E. Roth. The Handbook of Experimental Economics. Princeton University Press, 1995.
[5]. E.G. Gimenez-Funes, L. Godo, J. A. Rodriguez-Aguilar, and P.Garcia-Calves. Design Bidding Strategies for Trading Agents in Electronic Auctions. In Proceedings of International Conference on Multi Agents System, 1998, Page(s): 136 -143
[6]. Jining Hu and Michael P. Wellman. Online Learning about Other Agents in a Dynamic Multiagent System. In Proceeding of the Second International Conference on Autonomous Agents. (Agents-98)
[7]. Junling Hu, Daniel Reeves, and Hock-Shan Wong. Agent Service for Online Auctions. In Proceedings of the AAAI-99 Workshop on AI for Electronic Commerce.
[8]. J-S. R. Jang, C.-T. Sun and E. Mizutani. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Prentice-Hall, 1997.
[9]. Leslie Pack Kaelbling, Michael L Littman, and Andrew W. Moore. Reinforcement Learning: A Survey, Journal of Artificial Intelligence Research (1996), 4:237-285.
[10]. Ralph L. Keeney and Howard Raiffa. Decisions with Multiple Objectives: Preferences and Value Tradeoffs. Cambridge University Press 1993.
[11]. Andreu Mas-Colell, Michael D. Whiston and Jerry R. Green. Microeconomic Theory. Oxford University Press 1995.
[12]. R. Peterson McAfee and John McMillan. Auctions and Bidding. Journal of Economic Literature, Vol XXV, June 1987, pp. 699-738.
[13]. Tom M. Mitchell. Machine Learning. McGraw-Hill, 1997.
[14]. Chris Preist. Commodity trading using an agent-based iterated double auction. Proceedings of the third annual conference on Autonomous Agents, 1999, Pages 131 - 138
[15]. John Rust, John H. Miller, and Richard Palmer. Behavior of Trading Automata in a Computerized Double Auction Market. In [2]. pp. 155-198.
[16]. Abdolkarim Sadrieh. The Alternating Double Auction Market: A Game Theoretic and Experimental Investigation. Lecture Notes in Economics and Mathematics System 466. Springer, 1998.
[17]. Robert Wilson. Incentive Efficiency of Double Auctions. Econometrica, Sept. 1985, 53(5), pp. 1101-115.
[18]. Peter R. Wurman, Michael P. Wellman, and William E. Walsh. A Parameterization of The Auction Design Space. Available via http://www.csc.ncsu.edu/faculty/wurman/Papers/auction_parameters.ps.
[19]. Peter R. Wurman, William E. Walsh, and Michael P. Wellman. Flexible Double Auctions for Electronic Commerce: Theory and Implementation. Decision support systems 24, 1998, pp. 17-27.
[20]. Hal R. Varian. Microeconomics Analysis 3rd Edition . W. W. Norton & Company, 1992.
[21]. William Vickrey. Counterspeculation, Auctions, and Competitive Sealed Tenders. Journal of Finance, March 1961. 16(1). pp. 8-37.
[22]. J.M. Vidal and E.H. Durfee. The impact of nested agent models in an information economy. In Proceeding of the Second International Conference on Multiagent Systems, pp. 377-384, Menlo Park, CA, 1996. AAAI Press.
[23]. The Michigan AuctionBot. http://auction.eecs.umich.edu/
[24]. Sutton, R. S. (1988). Learning to Predict by the Methods of Temporal Differences. Machine Learning 3: 9-44.