1.
研究限制：本研究所受到的限制，如下所述：首先，因為數位遊戲有太多種類型，因此本 研究只能選擇其中一種來做實驗，並且結果無法一般化，是否有更好的方法可以應 用在所有的遊戲類型之中會是一個非常具有挑戰性的問題。另外在本研究的坦克對 戰類型遊戲中，為了瞭解增強式學習技術與模糊理論的實用性，本論文簡化了遊戲 的過程，讓 NPC 坦克的目標只是移動到玩家的陣地，但是實際的遊戲不應該是如 此簡單，在路徑中或許會有一些可以增益的道具或是不同的機關讓遊戲更有趣，在 這樣的情形下就需要有更多的因素加入在獎懲機制之中，並且反映到SARSA 演算 法中，因此未來可以研究多目標增強式學習運算方式。
2.
未來研究I. 如研究限制中所提到，如果除了懲罰因素(如本研究的炸彈)加入了獎勵因 素(如在本研究中加入替 NPC 坦克抵擋玩家攻擊之道具)，會有更複雜的情形 產生，在這樣的狀態下該如何應用增強式學習是一個值得研究的議題。
II. 另外，現在的數位遊戲常常是可以多人進行的，如果是可以多人進行的遊 戲，那NPCs 應該也會有不同的反應，同時如果是線上即時的遊戲時，那可能 會有更複雜的情形產生，如何有效的應用模糊增強式學習在這些複雜的情形下 也會是一個有趣的議題。
III. 除此之外還可以探討增強式學習中各種不同的演算法(q-learning 與 SARSA 等)應用在不同的遊戲類型上的表現等，在這其中仍然有許多的研究議 題值得深入去做研究。
52
參考文獻
11. Aha, D. W., Molineaux, M. and Ponsen, M. (2003), “Learning to Win: Case-Based Plan Selection in a Real-Time Strategy Game”, In Proceedings of the Sixth International Conference on Case-Based Reasoning, Trondheim, Norway, June 23-26, pp. 5-20.
12. Buckland, M.(2005), Programming game AI by example, Jones & Bartlett Publishers, Sudbury MA.
13. Bianchi, R. A. C. and Ribeiro, C. H.C. and Costa, A. H. R.(2007), “Heuristic selection of actions in multiagent reinforcement learning”, In Proceedings of the 20th International Joint Conference on Artifical Intelligence, India ,January 6-12, pp. 690-696.
53
14. Björnsson, Y., Hafsteinsson, V., Jóhannsson, A. and Jónsson, E.(2004), ”Efficient Use of Reinforcement Learning in A Computer Game”, In Proceedings of the International Conference on Computer Games: Artificial Intelligence, Design and Education, University of Wolverhampton, UK, November8-10, pp.379-383.
15. Barber, H. and Kudenko, D. (2007), “Adaptive Generation of Dilemma-based Interactive Narratives”, Advanced Intelligent Paradigms in Computer Games in Book series of Studies of Computational Intelligence (71), Springer Berlin / Heidelberg, pp.
19-37.
16. Bourg, D. M. and Seemann, G.(2004), AI for Game Developers, O'Reilly Media, Cambridge, Massachusetts.
17. Charles, D.(2004), "Enhancing Gameplay: Challenges for Artificial Intelligence in Digital. Games", LNCS 3166, Springer Berlin / Heidelberg, pp.57-108.
18. Ghory, I.(2004), ”Reinforcement learning in board games.”, Technical Report of Department of Computer Science , University of Bristol, England, UK
19. Graepel, T. Herbrich, R. and Gold, J. (2004), ”Learning to fight” , In Proceedings of the International Conference on Computer Games: Artificial Intelligence, Design and Education. University of Wolverhampton, UK, November8-10, pp.193-200.
20. Pieczy ski, A. and Obuchowicz, A.(2004), ” Application of the General Gaussian Membership Function for the Fuzzy Model Parameters Tunning”, LNCS 3070, Springer Berlin / Heidelberg, pp.350-355.
21. Jin, X. H., Jang, D. H. and Kim, T.Y.(2008), “Evolving Game NPCs Based on Concurrent Evolutionary Neural Networks” , LNCS 5093, Springer Berlin / Heidelberg, pp. 230–239.
22. Livingstone D. & Charles D(2004), “Intelligent Interfaces for Digital Games” , Springer Berlin / Heidelberg LNCS 3166, pp.57-108.
23. McPartland, M. and Gallagher, M.(2008), “Creating a Multi-Purpose First Person Shooter Bot with Reinforcement Learning”, In Proceedings of Computational Intelligence and Games, Perth, Australia, December 15-18, pp. 143-150.
24. Ponson, M et al.(2006), “Hierarchical Reinforcement Learning with Deictic”, In Proceedings of the 18th Belgium-Netherlands Conference on Artificial Intelligence (BNAIC 2006), University of Namur, Belgium, October 5-6, pp. 251-258.
25. Ponson, M. and Spronck, P.(2004), “Improving Adaptive game AI With Evolutionary Learning”, In proceedings of 15 th International Conference on Computer Games: AI,
54
Animation, Mobile, Interactive Multimedia, Educational & Serious Games, University of Wolverhampton, UK . pp. 389-396
26. Russell, S. and Norvig, P.(2003), Artificial Intelligence A Modern Approach, Prentice Hall, New Jersey.
27. Sutton, R. S. and A. G. Barto (1998). Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA.
28. Szita, I. and Lorincz, A.(2007), “Learning to Play Using Low-Complexity Rule-Based Policies:Illustrations through Ms. Pac-Man”, Journal of Artificial Intelligence Research (30) , pp.659-684
29. Seo, H.(2000), “A Fuzzy Reinforcement Function for the Intelligent Agent to process Vague Goals”. In Proceedings of the 19th IEEE International Conference of the North American Fuzzy Information Processing Society, Atlanta, Georgia, Usa, July 13-15, pp.29-33.
30. Spronck, P. , Ponsen, M. , Sprinkhuizen-Kuyper, I. , Postma, I. (2006), “Adaptive game AI with dynamic scripting”, Machine Learning (63), pp. 217–248
31. Wender, S. and Watson, I.(2008), “Using Reinforcement Learning for City Site Selection in the Turn-Based Strategy Game Civilization IV”, In proceedings of the International Conference on Computational Intelligence and Games, Perth, Australia, December 15-18, pp. 372-377.
32. Watkins, C. J. C. H. and P. Dayan (1992). “Q-learning”. Machine Learning (8), pp.279–292.
33. Zadeh, L.A. (1968). “Fuzzy Algorithms". Information and Control 12 (2), pp. 94–102.
網站：
34. 台灣經濟研究院(2008)。2010 年 6 月。全球消費性電子產品業產業研究報告，取 自：http://www.tier.org.tw。
(2010) 2010 年 6 月
35. 行政院六大新興產業主題網 。文化創意產業。 。取自：
http://www.ey.gov.tw/lp.asp?CtNode=3038&CtUnit=1254&BaseDSD=7&mp=97 。 36. 杭州電魂(2010)。夢三國。2010 年 7 月。取自：http://www.m3guo.com。
37. 資策會資訊市場情報中心(2008)。台灣遊戲市場發展現況與趨勢。2010 年 6 月。取 自：http://mic.iii.org.tw/aisp/。
38. Blizzard(2000), “world editor of warcraft III”, Retrieved May 20, 2009, from the World
55
Wide Web: http://classic.battle.net/war3/faq/worldeditor.shtml
39. Epstein, S. L.(1999), Games & Puzzles, Retrieved July 8, 2010, from the World Wide Web: http://www.aaai.org/AITopics/pmwiki/pmwiki.php/AITopics/Games
40. Melenchuk, P.(2000) ,”Reinforcement Learning”, Retrieved 15 May 2009, from the World Wide Web:
http://pages.cpsc.ucalgary.ca/~jacob/Courses/Winter2000/CPSC533/Pages/CPSC-533-C ourseOutlein.html
41. Riot games (2009).League of Lengends. Retrieved July 8, 2010, from the World Wide Web: http://www.leagueoflegends.com
42. S2 games (2010). Heroes of newerth. Retrieved July 8, 2010, from the World Wide Web:
http://www.heroesofnewerth.com
56