跳到主要內容

臺灣博碩士論文加值系統

(3.236.84.188) 您好!臺灣時間:2021/08/01 20:06
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:王文凱
研究生(外文):Wen-Kai Wang
論文名稱:多代理人系統中的混合學習與合作方法
論文名稱(外文):A Hybrid Learning Approach for multi-agent cooperation in RoboCup
指導教授:郭忠義郭忠義引用關係
口試委員:范姜永益劉建宏李允中
口試日期:2012-07-05
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電資碩士在職專班研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:46
中文關鍵詞:機器學習多代理人系統案例式推論基因演算法規則推論
外文關鍵詞:RoboCupMachine learningMulti-agent SystemCase Based ReasoningGenetic AlgorithmRule Based Reasoning
相關次數:
  • 被引用被引用:3
  • 點閱點閱:181
  • 評分評分:
  • 下載下載:33
  • 收藏至我的研究室書目清單書目收藏:1
在機器學習的議題中,學習效率為一個重要的研究方向。多代理人系統(Multi- Agent system)在動態變化的環境中,能夠透過學習而做出最佳的回應動作是個極具挑 戰性的問題。本篇研究針對多代理人系統問題提出一種混合式的技術架構,目的在於 讓代理人能夠在不需要太多相關背景知識的前提下能夠透過學習達到近似領域專家的 能力。
本研究結合了三種方法來建立一個多代理人的學習系統,利用案例式推論來累積 代理人的經驗,結合基因演算法來最佳化學習效率,並加以基本的規則庫來建立初始 經驗庫以及應付突發狀況。並基於 RoboCup 模擬平台(RoboCup Soccer simulator)建立 此混合技術架構為核心的足球隊。教練代理人透過比賽經驗的累積,能夠針對當下球 場上的動態做出更適合的決策,並建立球員代理人的合作模型讓多個球員代理人互相 分工合作來完成教練所下達的策略。透過多組實驗比較各方法對於代理人學習效率的 影響以及跟其他相關研究的分析與比較。

The problem of learning efficiency with multi-agent system is one of the most important tasks for machine learning area. It''s a complex challenge to design a multi-agent system and able to make the optimized response through learning in a dynamic environment. In this paper, we propose a hybrid approach that allows agents to learn and react as a domain expert with only little domain knowledge.
In this paper, three notable methods are used to construct a multi-agent learning system. Case Based Reasoning (CBR) is applied to accumulate experiences and Genetic Algorithm (GA) is used to optimize the learning efficiency. Rule Based Reasoning (RBR) is adopted to advance the CBR. A soccer team is built by our learning approach based on RoboCup soccer simulation environment.
The coach agent can make the proper strategies and get smarter as the experiences are accumulated. The cooperate-model allows player agents to work with each other for accomplishing all strategies that were made by coach agent.
Through experiments, we found how each method can affect the learning efficiency and game result.
Finally, we also compare our approach with other related researches.

摘 要 i
ABSTRACT ii
誌謝 iii
目錄 iv
表目錄 v
圖目錄 vi
第一章 緒論1
1.1 前言1
1.2 研究動機與目的1
1.3 研究貢獻1
1.4 章節編排.2
第二章 文獻探討3
2.1 BDI 代理人模型3
2.2 多代理人組合服務3
2.3 案例式推論4
2.4 基因演算法5
2.5 基因型案例式推論8
第三章 多代理人系統混合式學習架構10
3.1 代理人學習與合作模型10
3.2 推論流程15
3.3 推論設計16
第四章 系統實作與實驗24
4.1 問題描述24
4.2 系統設計25
4.3 系統實作26
4.4 實驗設計36
4.5 討論與實驗探討39
第五章 相關研究比較40
第六章 結論與未來展望.42
6.1 結論42
6.2 未來展望42
參考文獻43

[1] M. E. Bratman, “Intention, Plans, and Practical Reason,” Harvard University Press, 1987.
[2] A. S. Rao and M. P. Georgeff, “Modeling Rational Agents within a BDI-Architecture,” in Proceedings of the Second International Conference on Principles of Knowledge Representation and Reasoning, Morgan Kaufmann, San Mateo, California, USA, pp. 473-483, 1991.
[3] B. N. Schilit and M. M. Theimer, “Disseminating Active Map Information to Mobile Hosts, ” IEEE Network, vol. 8, no. 5, pp. 22-32, 1994.
[4] J.Y. Kuo and H.K. Cheng, “Applying Assimilation and Accommodation for Cooperative Learning of RoboCup Agent,” in Proceedings of International Conference on Machine Learning and Cybernetics, pp. 3234 - 3239, 2010.
[5] H.S. Su, X.F. Wang, and Z.L. Lin, “Flocking of Multi-Agents with a Virtual Leader,” IEEE Transactions on Automatic Control, vol. 54, no. 2, pp. 293-307, 2009.
[6] A. L. C. Bazzan, “Opportunities for Multiagent Systems and Multiagent Reinforcement Learning in Traffic Control,” Autonomous Agents and Multi-Agent Systems, vol. 18, no. 3, pp. 342-375, 2009
[7] P. R. Ferreira Jr et al., “RoboCup Rescue as Multi-Agent Task Allocation Among Teams: Experiments with Task Interdependencies,” Autonomous Agents and Multi- Agent Systems, vol. 20, no. 3, pp. 421-443, 2010.
[8] X. Chang, G. Jisuanji and Y. Yu, “RoboCup-2D Passing Strategy Based on Joint Reinforcement Learning,” Computer Engineering and Applications, vol. 47, no. 23, pp. 212-216, 2011.
[9] U. Ryuichi et al., “Dynamic Programming for Creating Cooperative Behavior of Two Soccer Robots - Part 1: Computation of State-Action Map,” in Proceedings of IEEE International Conference on Robotics and Automation, pp. 1-7, 2007.
[10] M. Brenner and B. Nebel, “Continual Planning and Acting in Dynamic Multi-Agent Environments,” Autonomous Agents and Multi-Agent Systems, vol. 19, no. 3, pp. 297- 331, 2009.
[11] J. Y. Kuo and F. C. Huang, “A hybrid Approach for Multi-Agent Learning Systems,” Intelligent Automation and Soft Computing, vol. 17, pp. 1-15, 2010.
[12] R. C. Schank, “Dynamic Memory: A Theory of Reminding and Learning in Computers and People,” Cambridge University Press, 1982.
[13] B. G. Silverman, “Knowledge-Based Systems and the Decision Sciences,” Interface, INFORMS , vol.25, no. 6, pp. 67-82, INFORMS, Hanover, Maryland, USA, 1995.
[14] M. W. Floyd, B. Esfandiari. and K. Lam, “A Case-based Reasoning Approach to Imitating RoboCup Players,” in Proceedings of Twenty-First International Florida Artificial Intelligence, pp. 251-256, 2008.
[15] M. W. Floyd and B. Esfandiari, “Toward a Domain-independent Case-based Reasoning Approach for Imitation: Three Case Studies in Gaming,” in Proceedings of Workshop on Case-Based Reasoning for Computer Games at the 18th International Conference on Case-Based Reasoning, pp. 55-64, 2010.
[16] T. Srinivasan et al., “CBRRoboSoc : An Efficient Planning Strategy for Robotic Soccer using Case Based Reasoning,” in Proceedings of International Conference on Intelligent Agents, Web Technologies and Internet Commerce, pp. 113, 2006
[17] J. Holland, “Adaptation in Natural and Artificial Systems,” University of Michigan Press, 1975.
[18] J. Aronsson, “Genetic Programming of Multi-agent System in the RoboCup Domain,” MD thesis, Lund Institute of Technology, Sweden, 2003.
[19] Z. Liu, K. Chen and L. Liu, “A Uniform Gait Generation Method for RoboCup Humanoid Robot Based on Genetic Algorithms,” in Proceedings of IEEE International Conference on Mechatronics and Automation, pp. 1620-1625, 2006.
[20] E. A. Fares, M. Elbardiny and M. M. Sharaf, “Adaptive Fuzzy Logic Controller of Visual Servoing Robot System by membership optimization using Genetic Algorithms,” in Proceedings of IEEE International Conference on ComputerEngineering and Systems, pp. 15-20, 2007.
[21] W. Bai, B. Xue and Y. Sun, “Research on Path Planning for Soccer Robot Based on Improved Genenic Algorithm,” in Proceedings of Mechatronic Science, Electric Engineering and Computer (MEC), pp. 1687-1690, 2011.
[22] S. Ghoshray and K. K. Yen, “More Efficient Genetic Algorithm For Solving Optimization Problems,” in Proceedings of IEEE International Conference on Systems, Man and Cybernetics, vol. 5, pp.4515-4520, 1995.
[23] K. S. Shin and I. Han, “Case-Based Reasoning Supported by Genetic Algorithms for Corporate Bond Rating,” Expert Systems with Applications, vol. 16, no. 2, pp. 85–95, 1999.
[24] G. Beddoe and S. Petrovic, “Selecting and Weighting Features Using a Genetic Algorithm in a Case-Based Reasoning Approach to Personnel Rostering,” European Journal of Operational Research, vol. 175, no. 2, pp. 649-671, 2006.
[25] Y. J. Park, S. H. Chun and B. C. Kim, “Cost-Sensitive Case-Based Reasoning Using a Genetic Algorithm: Application to Medical Diagnosis,” Artificial Intelligence in Medicine, vol. 51, no. 2, pp. 133-145, 2011.
[26] P. Liviu and L. Sean, “Cooperative Multi-Agent Learning The State of the Art,” Autonomous Agents and Multi-agent Systems, vol. 11, no. 3, pp. 387-434 , 2005.
[27] http://wrighteagle.org/en/robocup/2D
[28] W. Q. Liao and X. D. Zhou, “Soccer Robot Path-planning Based on Genetic Algorithms
in Dynamic Environment,” Journal of Jimei University (Natural Science), 2012.
[29] C. Kwok and D. Fox, “Reinforcement Learning for Sensing Strategies,” in Proceedings
of Intelligent Robots and Systems, vol. 4, pp. 3158-3163, 2004.
[30] Y. Takahashi and M. Asada, “Multi-Layered Learning Systems for Vision-based
Behavior Acquisition of A Real Mobile Robot,” in Proceedings of SICE Annual
Conference 2003, Fukui, pp. 2937-2942, 2003.
[31] Y. L. Yi and Y. Guan, “A Path Planning Method to Robot Soccer Based on Dijkstra
Algorithm,” Advances in Intelligent and Soft Computing, vol. 149, pp. 89-95. 2012
[32] C . Mericli, T. Mericli, and H. L. Akın, “A Reward Function Generation Method Using
Genetic Algorithms: A Robot Soccer Case Study,” in Proceedings of Conference on
Autonomous Agents and Multi-agent Systems (AAMAS 2010), pp. 1513-1514, 2010.
[33] T. Nakashima et al., “An Evolutionary Approach for Strategy Learning in RoboCup
Soccer,” in Proceedings of IEEE International Conference on Systems, Man and
Cybernetics, pp.2023-2028, 2004.
[34] C. Castillo, M. Lurgi, and I. Martinez, “Chimps: an Evolutionary Reinforcement
Learning Approach for Soccer Agents,” in Proceedings of IEEE International
Conference on System, Man and Cybernetics, vol.1, pp. 60-65, 2003
[35] S. Kinoshita and Y. Yamamoto, “Team 11 Monkeys Description,” in Proceeding on
RoboCup-99, pp. 154-156, 1999
[36] M. Veloso, “Teamwork Planning and Learning in Adversarial Multi-Robot Domains,”
Advances in Autonomous Mini Robots, pp. 5, 2012.
[37] K. S. Hwang, S. W. Tan, and C. C. Chen, “Cooperative Strategy Based on Adaptive Q-
Learning for Robot Soccer Systems,” IEEE Transactions on Fuzzy System, pp. 569-576, 2004
[38] M. W. Floyd and B. Esfandiari, “Toward a Domain Independent Case-Based Reasoning Approach for Imitation: Three case studies in gaming,” in Workshop on Case-Based Reasoning for Computer Games at the 18th International Conference on Case-Based Reasoning, pp.55–64, 2010.
[39] A. B. Gonzalez and J. A. R. Uresti. “Strategy Patterns Prediction Model,” Lecture Notes in Computer Science, vol. 7094, pp. 101-112, 2011.
[40] A. Bai et al., “WrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions,” in Proceedings of the RoboCup International Symposium 2011 (RoboCup 2011), 2011.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊