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:2021/08/04 23:15
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:張凱鈞
研究生(外文):Kai-Chung Chang
論文名稱:適應式學習的同化與調適應用於智慧型代理人系統
論文名稱(外文):Adaptive Learning of Assimilation and Accommodation for Intelligent Agent System
指導教授:郭忠義郭忠義引用關係許見章
指導教授(外文):Jong-Yih KuoChien-Chang Hsu
學位類別:碩士
校院名稱:輔仁大學
系所名稱:資訊工程學系
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:2007
畢業學年度:95
語文別:英文
論文頁數:56
中文關鍵詞:智慧型代理人適應式學習同化調適多代理人系統
外文關鍵詞:Intelligent AgentAdaptive LearningAssimilationAccommodationMulti-agent System
相關次數:
  • 被引用被引用:2
  • 點閱點閱:260
  • 評分評分:
  • 下載下載:40
  • 收藏至我的研究室書目清單書目收藏:0
適應式的學習廣泛的用在代理人學習上。合作學習用來改進收斂速度和學習的品質,對於多代理人的學習也是一個重要的能力。一個有彈性且簡單的方法對於多代理人的獨立學習與合作學習是必要的。
本篇論文提出一種適應式的方法來完成一種智慧型代理人的適應式學習方式。利用這種方法,代理人可以達成適應式的學習,且可以與其他代理人溝通來達成合作學習。
本篇論文針對智慧型代理人提出了一個知識處理循環週期,來揣摩人類的學習程序。在這個週期當中著重於兩個重要部分。同化的程序用於讓代理人學習資訊,調適的程序用於在當新資訊與代理人之前所學習到的知識產生衝突時,做解決並修正知識。代理人知識基礎我們用一個認知架構來表示,用這個認知架構來配合上述兩個程序做學習,這個認知架構我們將他對應到BDI的代理人架構上。
本篇論文利用一個可以簡單表達多代理人行為的追蹤者、逃避者問題來解釋我們的方法。並且針對多代理人,使用Java語言代理人發展架構 JADE (Java Agent DEvelopment Framework) 當作代理人開發平台來處理發展多代理人時的必要支援。
Adaptive learning is broadly used in agent learning. Cooperation learning is also a crucial ability in multi-agent system to improve the speed of convergence and quality of learning. A flexible also easily approach is needed for agents to learn individually and cooperatively.
This paper presents an adaptive approach to address a kind of adaptive learning for intelligent agent. The agent can learns adaptively, and can communicate with other agents for cooperative learning by using this adaptive process.
A knowledge processing cycle is proposed here for intelligent agent to mimic the human’s learning process. This process regards two important parts, the assimilation process for learning new information, the accommodation process for resolution when new information have some conflict with agent’s proper known. The cognitive structure is the representation of agent’s knowledge base which used on these two processes for learning, the structure here we fit it into BDI-agent model.
We use the pursuit-evasion game to explain our approach which can explain multi-agent’s behavior easily, and for multi-agent system we use the JADE (Java Agent DEvelopment Framework) as our agent platform to handle agent’s essential supports in development.
CHAPTER 1 INTRODUCTION 5
1.1 Motivation 5
1.2 Objective 6
1.3 Organization 7
CHAPTER2 RELATED WORK 8
2.1 BDI Agent Model 8
2.2 Piaget’s view of child learning 10
2.3 Assimilation and Accommodation 11
2.4 The Agent Learning Pattern 11
2.5 Cooperative Q-learning with Heterogeneity in Actions 14
CHAPTER 3 AGENT ADAPTIVE LEARNING 17
3.1 Agent Adaptive Model 17
3.2 Agent Assimilation and Accommodation 19
3.3 Agent’s Learning Cycle 25
CHAPTER 4 ASSIMILATION AND ACCOMMODATION FOR AGENTS’ COOPERATION AND COMPETITION 28
4.1 Pursuer Team and Evade Team 28
4.2 Agent’s Plan Generate 30
4.3 Pursuer Strategies Representation 31
4.4 Information Update and Strategy Design 35
CHAPTER 5 CASE STUDY 38
5.1 System Architecture 39
5.2 System Environment 41
5.3 System Implementation 42
5.4 Discussion 46
CHAPTER 6 CONCLUSION 52
[1]J.P. Hespanha, M. Prandini, and S. Sastry, “Probabilistic Pursuit-Evasion Games: Theory Implementation and Experimental Evaluation”, IEEE Transactions on robotic and automation, 2002.
[2]J. Piaget, “Cognitive development in children: development and learning”, Science teaching and the development of reasoning, U. of California, Berkeley. 1964.
[3]A. Rao, and M. Georgeff, “BDI Agents: From Theory to Practice”, International Conference on Multi-Agent Systems, 1995.
[4]J. Y. Kuo, M. L. Tsai, and N. L. Hsueh, “Goal Evolution based on Adaptive Q-learning for Intelligent Agent”, IEEE International Conference on Systems, Man and Cybernetics, 2006.
[5]S. Takamuku and R.C. Arkin, “Multi-method Learning and Assimilation”, Engineering, Osaka university, Georgia, Institute of Technology Atlanta, 2007.
[6]D. G. Cooper and L. Martin, “Agent Learning as A Control Problem”, Fifth Understanding Complex Systems Symposium, 2005.
[7]F. Zhang and D. Tan, “Motion Planning based on Relative Coordination in Dynamic Environments for Mobile Agent”, International Conference on Control, Automation, Robots and Vision Kunming, 2004.
[8]F. Zhang, D. Tan, Y. Wei, “Obstacle Avoidance for Mobile Robots Based on Relative Coordinates”, IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, 2003.
[9]C. Baray, “Evolving Cooperation via Communication in Homogeneous Multi-agent Systems”, Intelligent Information Systems, 1997.
[10]S. Abbasi, M.-R. Akbarzadeh-T, “Agent-based Cooperative Co-evolution for Fuzzy Systems”, World Automation Congress, 2004.
[11]L. Marques, A. Martins, and A. T. de Almeida, “Environmental Monitoring with Mobile Robots Intelligent Robots and Systems”, IEEE/RSJ International Conference, 2005.
[12]J. Hulstijn, F. Dignum, and M. Dastani, “Coherence Constraints for Agent Interaction”, AAMAS Workshop on Agent communication, LNCS 3396, 134-152, 2004.
[13]G. Nitschke, “Co-evolution of cooperation in a pursuit evasion game”, IEEE/RSJ International Conference on Intelligent Robots and Systems. Vol. 2, pp. 2037 – 2042, 2003.
[14]J. Y. Kuo, ”Fuzzy BDI Modeling For Intelligent Agent”, WSEAS Transactions on Systems, pp. 817-822, 2004.
[15]F. Bellifemine, A. Poggi, and G. Rimassa, “JADE - A FIPA-compliant agent framework”, Practical Applications of Intelligent Agents, pp. 97–108, 1999.
[16]A. Poggi, M. Tomaiuolo and P. Turci, “Extending JADE for Agent Grid Applications”, IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises, 2004.
[17]Z. Shen, C. Miao, A. Goh, and R. Gay, “Agent Mediated Grid Services in e-Learning”, IEEE International Symposium on Cluster Computing and the Grid, 2004.
[18]C. B˘adic˘, M. Ganzha, and M. Paprzycki, “Mobile Agents in a Multi-Agent E-Commerce System”, International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, 2005.
[19]J. A. R. P. Sardinha, A. F. Garcia, R. L. Milidiú, C. J. P. Lucena, “The Agent Learning Pattern”, Fourth Latin American Conference on Pattern Languages of Programming, 2004.
[20]J. P. Hespanha, H. J. Kim, and S. Sastry, “Multiple-Agent Probabilistic Pursuit-Evasion Games”, IEEE Conference of Decision and Control, pp. 2432-2437, 1999.
[21]A. Garcia, C.J.P. Lucena, , and D. Cowan, “Agents in Object-Oriented Software Engineering”, Software: Practice & Experience, Elsevier, pp. 489 - 521, 2004.
[22]M. Dastani, J. Hulstijn, F. Dignum, Meyer, J-J. Ch., “Issues in Multiagent System Development”, International Joint Conference on Autonomous Agents and Multi Agent Systems, ACM, pp. 922-929, 2004.
[23]J. Hulstijn, F. d. Boer, M. Dastani, F. Dignum, M. Kroese, J.J. Meyer, “Agent-based Programming in 3APL”, ICS Researchday, Conferentiecentrum Woudschoten, The Netherlands, 2003.
[24]A. R. DAMASIO, “Descartes' Error: Emotion, Reason, and the Human Brain”, G.P. Putnam, 1994.
[25]S. K. Sim, K. W. Ong and G. Seet, “A Foundation for Robot Learning”, Control and Automation, International Conference, pp. 649 – 653, 2003.
[26]A. A. Bitaghsir, A. Moghimi, M. Lesani, M. M. Keramati, M. N. Ahmadabadi, and B. N. Arabi, “Successful Cooperation between Heterogeneous Fuzzy Q-Learning Agents”, Systems, Man and Cybernetics, IEEE International Conference, pp. 5579 – 5583, 2004.
[27]S.M. Reza MirFattah, M.N. Ahmadabadi,., “Cooperative Q-learning with heterogeneity in actions”, Systems, Man and Cybernetics, IEEE International Conference, 2002.
[28]L. Martin, K. Greene, D. G. Cooper, A. L. Buczak, M. Czajkowski, J. L. Vagle, and M. O. Hofmann, “Cognitive Agents for Sense and Respond Logistics”, 2006.
[29]F. Liu and G. Zeng, “Multi-agent Cooperative Learning Research Based on Reinforcement Learning”, Computer Supported Cooperative Work in Design, International Conference, pp.1 – 6, 2006.
[30]Q. Zhang', Y. Yang, Y. Li, “A Multi-agent Cooperative System of Soccer Robot”, World Congress an Intelligent Control and Automation, 2002.
[31]T. Yoshidat, K. Horit, and S. Nakasukat, “A Reinforcement Learning Approach to Cooperative Problem Solving”, Multi Agent Systems International Conference, pp.479 – 480, 1998.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top