對於多代理人(Multi-Agent)、機器學習(Machine Learning)等研究領域而言，模擬機器人足球賽(Simulated RoboCup Soccer Games)是一個非常有趣的研究主題。如果你要贏得比賽的話，你必須有良好的基本技巧及協調整合一個隊的能力。在我們隊的架構中是以吸引力(Attractive Force)及排斥力(Repulsive Force)來決定球員移動的方向。另外我們設計了整隊策略(Team Strategy)及子策略(Sub-strategy)以做為我們比賽時所要執行的策略。我們使用了不同比重的向量來定義策略。在本篇論文中，我們使用了一種以經驗為基礎的監督學習的策略來選擇要執行傳球、射門或是運球等子策略。在傳球這個子策略中，我們以要接球球員的方向及距離做為我們選擇的考量。在射門這個子策略中，我們要考量的則是對方球門的方向及距離。如果不傳球也不射門的話則球員須運球。我們使用這個學習的策略來解決如何在子策略中轉換的問題。

RoboCup is an interesting topic in investigating into autonomous agents, multi-agent collaboration, machine learning and so on. If you want to win the match, you should have good basic skills and coordination. In our team architecture, we use attractive force and repulsive force to choose movement direction for a player. Furthermore, we design team strategy and sub-strategies to be our playing strategies. We use different weighted formula to express strategies. In this thesis, we use a memory-based supervised learning strategy to select execution sub-strategy from passing the ball, shooting the ball, and dribbling sub-strategy. We concentrate on the angle and direction of the critical player who catches the ball in passing the ball sub-strategy and the opponents’ goal in shooting the ball sub-strategy. We use this learning strategy to solve the problem of transference of sub-strategies and make it transfer rationally and smoothly.

1. Hiroaki Kitano, Monoru Asada, Yasuo Kuniyoshi, Itsuki Noda, Eiichi Osawa, Hitoshi Matsubara. RoboCup: A Challenge Problem for AI and Robotics. AI Magazine, 18(1):73-85, Spring 1997
2. Hiroaki Kitano, Monoru Asada, Yasuo Kuniyoshi, Itsuki Noda, Eiichi Osawa. RoboCup: The Robot World Cup Initiative. In Proc. of The First International Conference on Autonomous Agent (Agents-97)), Marina del Ray, The ACM Press, 1997.
3. Emiel Corten,Klaus Dorer, Fredrik Heintz, Kostas Kostiadis, Johan Kummeneje, Helmut Myritz, Itsuki Noda, Jukka Riekki, Patrick Riley, Peter Stone, Tralvex Yeap. Soccerserver Manual Ver. 5 Rev. 00 beta (for Soccerserver Ver.5.00 and later) http://www.dsv.su.se/~johank/RoboCup/manual/ver5.1release/browsable/ main.html
4. Hitoshi Matsubara, Itsuki Noda and Kazuo Hiraki. Learning of cooperative actions in multi-agent systems: a case study of pass play in soccer. AAAI-96 Spring Symposium on adaptation, Coevolution and Learning in Multiagent Systems.
5. Peter Stone and Manuela Veloso. A layered approach to learning client behaviors in the RoboCup soccer server. Applied Artificial Intelligence, 12:165-188, 1998.
6. Tung-Yiing Chiang. Coordinating Collaborative Strategies in Simulated Robotic Soccer Teams. Master Thesis, 1999.
7. Peter Stone and Manuela Veloso. “Multiagent systems: A survey from a machine learning perspective” IEEE Transactions on Knowledge and Data Engineering, June 1996.
8. Peter Stone and Manuela Veloso, CMUnited-97 Simulatior Team, In RoboCup-97: Robot World Cup I, Springer Verlag, Berlin, ed. By Hiroaki Kintano ,1998.
9. Susumu Takaki. The Reactive Motion Planing in the Passive Situation, In RoboCup-97: Robot World Cup I, Springer Verlag, Berlin, ed. By Hiroaki Kintano, 1998.
10. Peter Stone and Manuela Veloso. Beating a defender in robotic soccer: Memory-based learning of a continuous function. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 896-902, Cambridge, MA, 1996. MIT press.
11. Joerg P. Muller. The Design of Intelligent Agents—A Layered Approach, Springer, 1996.
12. Manuela Veloso, Peter Stone, and Michael Bowling. Anticipation: A Key for Collaboration in a Team of Agents, 3rd International Conference on Autonomous Agents, 1998.