动态多智能体建模与决策问题研究
|
摘要
复杂的动态决策问题是人工智能领域中复杂系统研究的一个重要组成部分。本文基于贝叶斯技术和决策理论，提出一种具有更强知识表示能力的动态决策模型——多Agent动态影响图，用于动态环境中的多智能体建模；探讨了多Agent动态影响图概率分布的近似计算方法、推理算法，以及多智能体的协作问题。全文主要内容及创新之处如下：
(1)给出了影响图的一种结构分解方法，将影响图分解成概率网络结构部分和效用结构部分；提出一种融合结构先验知识的MDL评分标准以降低传统MDL评分标准对数据的依赖性，并基于该评分标准提出一种PS-EM算法用于概率网络结构部分的模型选择；通过将联合效用函数表示成各个局部效用函数的和，进而构造一种用于学习局部效用函数的BP神经网络实现影响图效用结构部分的学习。实验结果表明了该模型选择方法的有效性。
(2)通过对相关概率决策模型的分析，将多Agent影响图在时间上进行扩展，提出一种新决策模型——多Agent动态影响图(MADIDs)，用于表示动态环境中多Agent协作关系。为了有效地计算MADIDs的概率分布，以Agents之间的策略相关性为指导，给出一种概率分布的分层分解方法，并基于KL差分对近似分布的误差进行了分析。
(3)针对MADIDs的1.5片联合树精确推理算法计算复杂性高和BK近似推理算法误差大的问题，提出一种扩展的BK(EBK)算法。EBK算法通过对MADIDs的概率分布进行分层分解来提高推理的计算效率，通过引入分割团来减小算法的推理误差，并且添加了效用结点和决策结点的推理。针对粒子滤波推理算法计算上维数过高和因式粒子滤波推理算法误差过大的问题，将粒子滤波和联合树推理算法的优点相结合，提出了一种联合树因式粒子推理(JFP)算法。JFP算法将MADIDs的概率分布转变成局部因式形式以提高计算效率，并利用联合树来传播因式粒子以减少推理误差。在仿真足球机器人中的一个局部协作模型上，对上面的各种算法进行了实验验证。
(4)在基于协作图实现多Agent协作方法的基础上，将角色引入协作图中给出了一种扩展的协作图，以减少协作中的通信。给出一种基于MADIDs的多Agent协作方法，通过环境的推理和局部效用的计算实现协作。通过对对手建模避免局部协作的通信。
The complex dynamic decision problem is an important part of the complex system research in Artificial Intelligence domain. Based on Bayesian technology and decision theory, Multi-Agent Dynamic Influence Diagrams(MADIDs) model is presented for modeling the dynamic Multi-Agent system, which is a dynamic decision model with more strong knowledge representation ability. The method of approximating distribution, inference algorithms and Multi-Agent coordination are discussed. The main research contents and innovations in this dissertation are as follows:
(1) A structural decomposition method of Influence Diagrams(IDs) is presented, and an Influence Diagram can be composed into two parts: probability structure and utility structure. A new MDL scoring is presented for reducing dependency on data, which merges the prior knowledge of network structures. Based on the new MDL scoring, a PS-EM algorithm is proposed for learning probability structure of IDs. The utility function of IDs is the sum form of the each local utility function, and a Neural Network is constructed for learning local utility functions of utility part. The experiment results show that PS-EM algorithm is efficient.
(2) Based on analyzing some probability decision models, Multi-Agent Dynamic Influence Diagrams(MADIDs) are presented by introducing a temporal aspect into the framework of MAIDs, and coordination relationships in dynamic environment can be modeled. To efficiently compute the probability distribution of MADIDs, a method of hierarchical decomposition is presented for approximating distribution of MADIDs under the guidance of the strategic relativity among Agents, and the errors are analyzed based on the KL divergence.
(3) Aimming at the high computation complexity of the 1.5 slice junction tree exact inference algorithm and the large error of BK approximate inference algorithm, an extensional BK (EBK) approximate inference algorithm is proposed. MADIDs are hierarchically decomposed for improving the efficiency of inference in EBK algorithm, and the conditionally independent separators are induced for decreasing the error of the inference, and the inference of decision nodes and utility nodes are added for inferring MADIDs. The particle filter algorithm and factored particle algorithm are discussed, and a junction tree factored particle filter(JFP) algorithm is presented by combing the advantages of the junction trees and particle filter. JFP algorithm converts the distribution of MADIDs into the local factorial form for improving computational efficiency; For decreasing error, the inference is performed by propagating factor particle on junction tree. Some simulative experiments are performed in the RoboCup simulation environment to verify and compare above algorithms, the results of which are quite satisfactory.
(4) The method of Multi-Agent Coordination using Coordination Graph (CG) is discussed; further, an extensional Coordination Graph is presented by inductting roles into CG to decrease the coordination communication. A Multi-Agent Coordination method is given based on MADIDs, where the coordination is realized by inference of environment and computation of local utility; and the communication of local coordination is avoided by modeling the opponent.
(1)给出了影响图的一种结构分解方法，将影响图分解成概率网络结构部分和效用结构部分；提出一种融合结构先验知识的MDL评分标准以降低传统MDL评分标准对数据的依赖性，并基于该评分标准提出一种PS-EM算法用于概率网络结构部分的模型选择；通过将联合效用函数表示成各个局部效用函数的和，进而构造一种用于学习局部效用函数的BP神经网络实现影响图效用结构部分的学习。实验结果表明了该模型选择方法的有效性。
(2)通过对相关概率决策模型的分析，将多Agent影响图在时间上进行扩展，提出一种新决策模型——多Agent动态影响图(MADIDs)，用于表示动态环境中多Agent协作关系。为了有效地计算MADIDs的概率分布，以Agents之间的策略相关性为指导，给出一种概率分布的分层分解方法，并基于KL差分对近似分布的误差进行了分析。
(3)针对MADIDs的1.5片联合树精确推理算法计算复杂性高和BK近似推理算法误差大的问题，提出一种扩展的BK(EBK)算法。EBK算法通过对MADIDs的概率分布进行分层分解来提高推理的计算效率，通过引入分割团来减小算法的推理误差，并且添加了效用结点和决策结点的推理。针对粒子滤波推理算法计算上维数过高和因式粒子滤波推理算法误差过大的问题，将粒子滤波和联合树推理算法的优点相结合，提出了一种联合树因式粒子推理(JFP)算法。JFP算法将MADIDs的概率分布转变成局部因式形式以提高计算效率，并利用联合树来传播因式粒子以减少推理误差。在仿真足球机器人中的一个局部协作模型上，对上面的各种算法进行了实验验证。
(4)在基于协作图实现多Agent协作方法的基础上，将角色引入协作图中给出了一种扩展的协作图，以减少协作中的通信。给出一种基于MADIDs的多Agent协作方法，通过环境的推理和局部效用的计算实现协作。通过对对手建模避免局部协作的通信。
The complex dynamic decision problem is an important part of the complex system research in Artificial Intelligence domain. Based on Bayesian technology and decision theory, Multi-Agent Dynamic Influence Diagrams(MADIDs) model is presented for modeling the dynamic Multi-Agent system, which is a dynamic decision model with more strong knowledge representation ability. The method of approximating distribution, inference algorithms and Multi-Agent coordination are discussed. The main research contents and innovations in this dissertation are as follows:
(1) A structural decomposition method of Influence Diagrams(IDs) is presented, and an Influence Diagram can be composed into two parts: probability structure and utility structure. A new MDL scoring is presented for reducing dependency on data, which merges the prior knowledge of network structures. Based on the new MDL scoring, a PS-EM algorithm is proposed for learning probability structure of IDs. The utility function of IDs is the sum form of the each local utility function, and a Neural Network is constructed for learning local utility functions of utility part. The experiment results show that PS-EM algorithm is efficient.
(2) Based on analyzing some probability decision models, Multi-Agent Dynamic Influence Diagrams(MADIDs) are presented by introducing a temporal aspect into the framework of MAIDs, and coordination relationships in dynamic environment can be modeled. To efficiently compute the probability distribution of MADIDs, a method of hierarchical decomposition is presented for approximating distribution of MADIDs under the guidance of the strategic relativity among Agents, and the errors are analyzed based on the KL divergence.
(3) Aimming at the high computation complexity of the 1.5 slice junction tree exact inference algorithm and the large error of BK approximate inference algorithm, an extensional BK (EBK) approximate inference algorithm is proposed. MADIDs are hierarchically decomposed for improving the efficiency of inference in EBK algorithm, and the conditionally independent separators are induced for decreasing the error of the inference, and the inference of decision nodes and utility nodes are added for inferring MADIDs. The particle filter algorithm and factored particle algorithm are discussed, and a junction tree factored particle filter(JFP) algorithm is presented by combing the advantages of the junction trees and particle filter. JFP algorithm converts the distribution of MADIDs into the local factorial form for improving computational efficiency; For decreasing error, the inference is performed by propagating factor particle on junction tree. Some simulative experiments are performed in the RoboCup simulation environment to verify and compare above algorithms, the results of which are quite satisfactory.
(4) The method of Multi-Agent Coordination using Coordination Graph (CG) is discussed; further, an extensional Coordination Graph is presented by inductting roles into CG to decrease the coordination communication. A Multi-Agent Coordination method is given based on MADIDs, where the coordination is realized by inference of environment and computation of local utility; and the communication of local coordination is avoided by modeling the opponent.
引文
[1]Kaynak, M.N.; Qi Zhi; Cheok, A.D.; Sengnpta, K.; Analysis of lip geometric features for audio-visual speech recognition. Systems, Man and Cybernetics, Part A, IEEE Transactions on. 2004,34(4):564-570
[2]Kumar, B.R.; Shanmugam, J.; Janarthanan, S.;Development of expert system for the design of airborne equipment. Digital Avionics Systems Conference, 2004. The 23rd.2004,2:24-28
[3]Yan-Qing Zhang; Constructive granular systems with universal approximation and fast knowledge discovery. Fuzzy Systems, IEEE Transactions on. 2005, 13(1):48-57
[4]Melby, N.J.; Comparative relative strength in artificial immune systems: system wellness. Southeast Con, 2005. Proceedings. IEEE. 2005,4:368-371
[5]Yang BS. Optimum design of short journal bearings by artificial life algorithm. Tribology, 2001,34(7):427-435
[6]Shichun Mei etc. An Adaptive Digital Watermarking Algorithm Based on Neural Network. Communication Fournal,2002,23(12):47-53
[7]Shaout A, Scharboneau J. Fuzzy Logic Based Modification System for the Learning Rate in Back propagation. Computers and Electrical Engineering,2000, 26(2): 125-139
[8]Yeung, D.S.; Degang Chen; Tsang, E.C.C.; On the generalization of fuzzy rough sets. Fuzzy Systems, IEEE Transactions on. 2005,13(3):343-361
[9]Tchignirinskaia L, Lu S, Molz F J, et al. Multifractal Versus Monofractal Analysis of Wetland Topography. Stochastic Environmental Research and Risk Assessment, 2000,(14):8-32
[10]Amigoni, F.;,Beda, A.;,Gatti, N.. Combining rate-adaptive cardiac pacing algorithms via multiagent negotiation. Information Technology in Biomedicine, IEEE Transactions on. 2006,10(1):11-18
[11]Pearl J.Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference[M].Morgan Kaufmann, Inc.San Mateo,CA 1988:185-189
[12]K. Hu, Y. Lu, C. Shi, Incremental Association Rule Mining: A Concept Lattice Approach.In: Ning Z, Lizhu Z. Eds. Proc. of PAKDD-99. Springer, 1999:109-113
[13]Ferguson, ThomasS. Development of the decision model of On the History of Statistics and Probability. Donald B.Owenr,1976:335-346
[14]N. Oliver, B. Rosario. A Bayesian computer vision system for modeling human interactions. IEEE Trans. Pattern Anal. Mach. Intell. 2000,22(8):831-843
[15]宋志伟，陈小平．仿真机器人足球中的强化学习．机器人，2003，25(7)：761-766
[16]R.A.Howard and J.E.Matheson. Influence diagrams. In R.A.Howard, Readings on the Principles and Applications of Decision Analysis. 1981,2:719-792
[17]Madsen, A.L. and D.Nilsson. Solving influence diagrams using HUGIN, Shafer-Shenoy and Lazy propagation. Uncertainty in Artificial Intelligence, 2001,17:337-345
[18]B.Banerjee,A.Bisjee,A.Biswas. Using Bayesian Netoworks to Model Agent Relationships. Applied Artif. Intelligence Journal. 2000,14(9):867-880
[19]S.Noh and P.J.Gmytrasiewicz. Agent modeling in antiarir defense. In Proceedings of the Sixth International Conference on User Modeling. 1997,6:389-400
[20]Kal Virtanen, Tuomas Ralvio. An Influence Diagram Approach to One-on-One Air Combat. 10th on Dynamic Games and Applications (ISDG2002), Russia. 2002, 7:12-15
[21]Mauricio Marengoni. Decision Making and Uncertainty Management in a 3D Reconstruction System. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003,25(7) 852-858
[22]Shenoy. Valuation_based systems for Bayesian decision analysis.Operations Research, 1992, 40:463-84
[23]D.Koller and B.Milch. Multi-agent influence diagrams for representing and solving games. In IJCAI-01,2001:1027-1036
[24]Avi Pfeffer, Ya'akov Gal. A Language for Descriptive Decision and Game Theory. AAMAS 2003, Melbourne, Victoria, Australia, Proceedings. ACM 2003:265-272
[25]Chung-Lin Huang; Huang-Chia Shih; Chung-Yuan Chao. Semantic analysis of soccer video using dynamic Bayesian network. Multimedia, IEEE Transactions on. 2006,8(4):749-760
[26]Ghahramani,Z. An introduction to Hidden Markov models and Bayesian Network. Int. Journal of pattern Recognition and Artificial Intelligence, 2001, 15(1):39-43
[27]Zweig, G.G. Speech Recognition with Dynamic Bayesian Networks. Ph.D.thesis, University of California, Berkeley.
[28]方帅，薛方正，徐心和．基于背景建模的动态目标检测算法的研究与仿真．系统仿真学报．2005，17(1)：159-161
[29]Kim SY, Imoto S,Miyano S.Inferring gene networks from time series microarray data using dynamic Bayesian networks.Brief Bioinform 2003;4:228-235
[30]D.Koller and R.Parr.Computing factored value functions for policies in structured MDPs.In IJCAI-99, 1999:1332-1339
[31]M.T.J.Spaan and F.C.A.Groen. Team coordination among robotic soccer players. In G.Kaminka, P.U.Lima, editors,Robocup2002. Spring-Verlag
[32]C.Boutilier. Sequential optimality and coordination in multi-agent systems. In IJCAI-99, 1999:478-485
[33]王红卫，李琛，刘会新．马尔可夫决策过程复杂性的熵测度．控制与决策，2004，19(9)：983-987
[34]Mauricio Marengoni. Decision Making and Uncertainty Management in a 3D Reconstruction System IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(7):852-858
[35]Barto, A. O., and Mahadevan. Recent Advances in Hierarchical Reinforcement Learning. Discrete Event Dynamic Systems. Theory and Applications, 2003, 13 (1/2):41-77
[36]P.Dagum and M.Luby, Approximating probabilistic inference using Bayesian networks is NP-hard,Artificial Intelligence.60(1), 1993:141-153
[37]F.R.BACH, M.I.JORDAN. Tin junction trees. In T. G. Dietterich, S.Becher, editors. Advances in Neural Information Processing Systems, 2002:569-576.
[38]S.Kirshner, P.Smyth. Conditional Chow-Liu tree structures for modeling discrete-valued vector time series. Technical. Report 04-04,School of information and computer Science, University of California, Irvine, 2004
[39]M.A.Paskin. Thin junction tree filters frontier for simultaneous localization and mapping. In Proc. Of IJCAI-03,2003:1157-1164.
[40]U.FEIGE,M.Hajiaghayi. Improved approximation algorithms for minimum-weight verter separators, in Proc. the 37th ACM Symposium on Theory of Computing, 2005.5:563-572
[41]Pedro Larranaga,Cindy M.H.Kuijpers. Decomposing Bayesian networks: triangulation of the moral graph with genetic algorithms Statistics and Computing 1997:19-34
[42]A.Beygelzimer and I.Rish. Inference complexity as a model-section criterion for learning Bayesian nwtworks. In Proceedings of the Eighth International Conference on Principles of Knowledge Representation and Reasoning(KR2002),Toulouse,France,2002
[43]F.V.Jensen, A.L.Madsen, LAZY propagation. A junction tree inference algorithm based on lazy evaluation. Artificial Intelligence. 1999,(113): 203-245
[44]D.Draper. Clustering without triangulation. Proc.UAI-95,1995:125-133
[45]K.Murphy and Y.Weiss. The factored frontier algorithm for approximate inference in DBNs. In Proc. Of UAI-01,2001:378-385
[46]周本达，王浩，姚宏亮．1 1／2片联合树算法在动态贝叶斯网精确推理中的应用．计算机工程与应用，2005，41(14)：81-84
[47]X.Boyen and D.Kollen. Tractable inference for complex stochastic processes. In Proc. Of UAI-98,1998:33-42
[48]K.Murphy and Y.Weiss. The factored frontier algorithm for approximate inference in DBNs. In Proc. Of UAI-01,2001:378-385
[49]M.A.Paskin. Thin junction tree filters for simultaneous localization and mapping. In proc. Of IJCAI-03,2003:1157-1164
[50]S.Arulampalam, S.Maskell,N. Gordon. A tutorial on particle filters for on-line non-linear/non Gaussian Bayesian tracking. IEEE Tran. On Signal Processing,2002,50(2):174-188
[51]A.Doucet. N.de Freitas, K.Murphy. Rao-blackwellised particle filtering for dynamic Bayesian networks. In Proceedings of the UAI-16th, 2000:253-259
[52]NG.B.,Pfeffer, A.,Dearden, R., and Hutter. Factored sampling for monitoring nonlinear hybrid systems with autonomous transitions. Submitted to the Conference on Uncertainty in Artificial Intellingence,2004.
[53]Wooldridge M J, Jennings N R. Intelligent agent: theory and practice [J]. Knowledge Engineering Review, 1995,10(2): 115-152
[54]Burkhard, H.D.; Duhaut, D.; Fujita, M.; Lima, P.; The road to RoboCup 2050[J]. Robotics & Automation Magazine, IEEE. 2002,9(2):31-38
[55]Dicky Suryadi and Piotr J.Gmytrasiewicz. Learning Models of Agents Using Influence Diagrams. IJCAI-99, 1999.8
[56]Scherrer, B.; Charpillet, F.; Cooperative co-learning: a model-based approach for solving multi-agent reinforcement problems Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings. 14th IEEE International Conference on. 2002, (10):463-468
[57]C.Guestrin, D Koller. Context-specific multiagent coordination and planning with factored MDPs. In AAAI 8th Nation conf on Artificial Intellingence, 2002,07:253-259
[58]王骋，王浩，方宝富．使用基于值规则的协作图实现多agent的动作选择．计算机工程与应用，2004，40(19)：61-62
[59]薛方正，方帅，徐心和．基于离散变量动作空间的多移动机器人对抗策略系统．东北大学 学报，2004，12：1138-1141
[60]THOMAS D.NIELSENi, FINN V. Learning a decision maker's utility function from (possibly) inconsistent behavior. Artificial Intelligence, 2004,160:53-78
[61]Sandholm T, Lesser V. Coalition among computationally bounded agents [J]. Artificial Intelligence, 1997,94(1): 99-137
[62]Zlotkin, G, Rosenschein J S. Domain theory for task oriented negotiation. Proceedings of the 13th International Joint Conference on Artificial Intelligence[C]. Morgan Kaufmann Publ Inc, 1993,416-422
[63]R.A.HOWARD and J.E.MATHESON. Influence diagrams[R]. Readings on the Principles and Applications of Decision Analysis. 1984:719-792.
[64]A.P. DAWLD. Influence Diagrams for Causal Modeling and Inference[J]. International Statistical Review, 2002,70(2):161-189.
[65]CHARNES and SHENOY. Multistage Monte Carlo Method for Solving Influence Diagrams[J]. Management Science. 2004,50(3):405-418
[66]D.HECKERMAN, D.GEIGER. Learning Bayesian networks: the combination of knowledge and statistical data[J]. Machine Leaning. 1995, 20(3): 197-243
[67]U.CHAJEWSKA, D.KOLLER. Utilities as random variables: density estimation and structure discovery[C], Proceedings of the Sixteenth Conference on Uncertainty in Artificeal Intelligence, Stanford,CA. 2000:63-71
[68]P.LARRANAGA, C.KUIJPERS. Learning Bayesian Network Structures by Searching for the Best Ordering with Genetic Algorithms[J],IEE Tons, Systems,Man,and Cybernetics, 1996,26(4):487-493
[69]王双成，苑森淼．具有丢失数据的贝叶斯网络结构学习研究[J]．软件学报，2004，15(7)：1042-1048
[70]XIAO-LIN Li, SEN-MIAO YUAN. Learning Bayesian Networks Structures based on extending evolutionary programming. Pro. Of the Third international conference on Machine Learning and Cybernetics, 2004:26-29
[71]Nir Friedman. The Bayesian structural EM algorithm. In Uncertuinty in Artificial Intelligence: Proceedings of the Fourteenth Conference(UAI),1998, 129-138
[72]LIU DY, WANG F, LU YN et.al.. Research on learning Bayesian network structure based on genetic algorithm[J]. Journal of Computer Research and Development, 2001,38(8):916-922
[73]P.TURNER, G. MONTAGUE. Nonlinear and direction-dependent dynamic process modeling using neural networks[C]. IEEE Proc. Control Theory Appl, 1996, 143(1):44-48
[74]A.S.D'AVIILA GARCEZ, K.BRODA. Neural-Symbolic Learning Systems: Foundations and Applications. Perspectives in Neural Computing. Springer-Verlag, 2002
[75]K.Murphy.The hayes net toolbox for matlab. Computing Science aad Statistics, 2001,33:331-351
[76]D.Koller. and B. Milch. Multi-agent influence diagrams for representing and solving games[C]. In IJCAI., 2001: 1024-1034
[77]Y.Gal and A.Pfeffer. A language for modeling Agents decision making processes in games[C]. In Proc. AAMAS-2nd, 2003
[78]Zhong-Yu Zhang, Wei-Yu Liu, Wei-Hua Li. Dynamic multi-gem influence diagrams for modeling multistage games[C]. Proc. 2002 International Conference on Machine Learning and Cybernetics, 2002:1184-1188
[79]Hongliang Yao, Hao Wang, Yousheng, Zhang,Junzhao Li. An Extensional Junction Tree Approximate Inference Algorithm for Dynamic Influence Diagrams. IEEE Proceedings of 2005 International Conference on Neural Networks. 2005,10:396-400
[80]Yao Hongliang, Wang Hao, ZhangYouSheng.Simplifying Computation of Dynamic Influence Diagrams. IEEE the Third International Conference on Machine Learning and Cybenetics ,Shanghai.2004, 8:59-62
[81]王浩．基于影响图的多Agent决策问题研究．合肥工业大学学报，2005，28(9)：1112-1116
[82]P.Dagum and M.Luby, Approximating probabilistic inference using Bayesian networks is NP-hard,Artificial Intelligence[J]. 1993, 60(1): 141-153
[83]田凤占，张宏伟，陆玉昌，石纯一．多模块贝叶斯网络中推理的简化[J]．计算机研究与发展，2003，40(8)：1230-1237
[84]U.Kjaerulff. Reduction of computational complexity in Bayesian networks through removal of weak dependences. In UAI-94, 1994:374-382
[85]Rached, Z., Alajaji, F., Campbell, L.L.. The Kullback-Leibler divergence rate between Matkov sources Information Theory, IEEE Transactions on. 2004, 50(5):917-921
[86]Shenoy, p.p ,"Valuation_based systems for Bayesian decision analysis." Operations Research, 1992,40:63-84
[87]Madsen,A.L. Lazy propagation:A junction tree inference algorithm based on lazy evaluation. Artificial Intelligence, 1999, 113:203-245.
[88]Nilsson, D. and Lauritzen, S.. Evaluating influence diagrams using LIMIDs. In Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann, Stanford, California. 2000:436-450
[89]William B. Davis. Graphical Model Theory for Wireless Sensor Networks. Lawrence Berkeley National Laboratory. Paper LBNL-53452 December8, 2002
[90]U. Kjaerulff, Optimal decomposition of probabilistic networks by simulated annealing,Stat.and compu. 1992(2):7-17
[91]Pedro Larranaga, Cindy M.H.Kuijpers,Mikel Poza and Robertoh.Murga Decomposing Bayesian networks:triangulation of the moral graph with genetic algorithms Statistics and Computing, 1997:19-34
[92]Wittig T, ed. ARCHON: An Architecture for multiagent systems [M]. Ellis Horwood, Chichester, United Kingdom, 1992
[93]Jennings N R, Mamdani E H, Corera J M, et al. Using Archon to develop real-world DAI applications[J]. IEEE Intelligent Systems and Their Applications, 1996, 11(6): 64-70
[94]P.Larranaga, C.Kuijpers,R.Murga, and Y.Yurramendi. Learning Bayesian Network Structures by Searching for the Best Ordering with Genetic Algorithms.IEEE Trans,Systems,Man, and Cybernetics, 1996,26(4):487-493
[95]Josep Roure,Ramon Sanguesa. Incremental Methods for Bayesian Network Learning, September 20,1999.
[96]B.Banerjee,A.Bisjee,A.Biswas. Using Bayesian Netoworks to Model Agent Relationships. Applied Artif. Intelligence Journal, 2000, 14(9):867-880
[97]M.Kearns, M.Littman. Graphical models for game theory. In UAI, 2001:253-260
[98]Boutilier C, Dearden R, Goldszmidt M. Stochastic dynamic programming with factored representations. Artificial Intelligence,2000,121(1-2):49-107
[99]Fengzhan Tian and Yuchang Lu. A DBN inference algorithm using junction tree. In Proc of the 5 world congress on intelligent control and Automation, 2004, 6:4236-4240
[100]R.Dechter.Bucket elimination: A unifying framework for probabilistic inference. In Proceedings of the Twelfth Conference on Uncertainty in Articial Intelligence(UAI-96), 1996
[101]N de Freitas. Rao-Blackwellised particle filtering for fault diagnosis. IEEE Aerospace, 2002,4:1767-1772
[102]A Doucet. On sequential simulation-based methods for Bayesian filtering, Department of Engineering, Cambridge University, Technical report CUED/F-INFENG/TR.310,1998
[103]D Fox. KLD-sampling: Adaptive particle filters. Advances in Neural Information Processing Systems 14 (NIPS), 2001
[104]Rached, Z.; Alajaji, F.; Campbell, L.L.; The Kullback-Leibler divergence rate between Markov sources Information Theory[J]. IEEE Transactions on, 2004, 50(5):917-921
[105]E.Levin.R.Pie Vaccini,and w.Eckert. A Stochastic Model of human-machine Interaction for learning processing. 2000, 8(1):11-23
[106]M.Asada, E.Uchibe. Cooperative behaviour acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development. Artificial Intelligence. 1999,110:276-292
[107]M.J.Mataric. Reinforcement learning in the multi-robot domain. Autonomous Robots, 1997,4:77-83
[108]L.locchi,D.Nardi.Distributed coordination in heterogeneous multi-robot systems. Autonomous Robots, 2003,15:155-168.
[109]M.J.Mataric, G.S.Sukhatme. Multi-robot task allocation in uncertain environments. Autonomous Robots, 2003,14:255-263
[110]A.Merkre and M.Riedmiller. A reinforcement learning approach to robotic soccer. In Robocup 2001,2001:435-440
[111]史忠植．智能主体及其应用[M]．北京：科学出版社，2000
[112]蔡自兴，艾真体——分布式人工智能研究的新课题[J]．计算机科学，2002,29(12)：123-126
[113]胡山立，石纯一．一种任意时间联盟结构生成算法[J]．软件学报，2001，12(5)：729-734
[114](美)S Russell，P Norvig著，姜哲，金奕江等人译．人工智能——一种现代方法(第二版)．人民邮电出版社,2003
[115]胡士强，敬忠良．粒子滤波算法综述．控制与决策．2005,20(4)：361-365
[116]张润梅，王浩，姚宏亮，方宝富．一种基于影响图的决策方法及在Robocup中的应用．系统仿真学报，2005,17(1)：134-137
[117]姜卯生，王浩，姚宏亮．朴素贝叶斯分类器增量学习序列算法研究．计算机工程和应用,2004,40(17)：57—59
[118]Vermaak J.Particle methods for Bayesian modeling and enhancement of speech signals [J].IEEE Trans Audo Speech Processing,2002,10(3): 173-185
[119]Guestrin CE, Koller D, Parr R. Efficient solution algorithms for factored MDPs. Journal of Artificial Intelligence Research. 2003,19:399-468
[120]高建清，王浩，于磊，方宝富．一种模糊强化学习算法及其在RoboCup中的应用．计算机工程与应用．2006．42(6)：52-54
[121]MUN Wai Lee, ISAAC Cohen, SOON Ki Jung, Particle filter with analytical inference for human body tracking. IEEE Workshop on Motion and Video Computing. Florida:IEEE, 2002:159-165
[122]于磊，王浩．Robocup中传球策略研究．计算机工程与应用，2004．40(28)：59-69
[123]姚宏亮，王浩，胡学钢，汪荣贵．基于遗传算法和MDL原则的贝叶斯网络结构优化算法．南京大学学报(自然科学版)，2002，38(11)：23-27
[124]姚宏亮，王浩，方宝富，胡学钢．基于影响图和动态贝叶斯网络的多Agent系统 中国人工智能进展，中国人工智能学会第10届全国学术年会．北京邮电大学出版社，2003，11：242-247
[125]汪荣贵，张佑生，王浩．分组样本下先验BN模型及条件概率的学习算法．微电子学与计算机．2002，19(5)：1-3
[126]H.H.Bui,D.H.Kieronska, and S.Venkatesh. Learning other agent" prefercenees in multiagent negotiation. in :Proc. of the 13th Nat. conf. on Artif. Intell.,Cambridge, 1996:114-119
[127]S.Sen and M.Sekaran. Individual learning of coordination knowledge, Journal of Experimental Theoretical Artificial lntelligence, 1998,10:333-356
[128]S.Sen,N.Arora, S.Roychowdhury. Using limited information to enhance group stability.International Jorunal of Human_Computer Studies, 1998, 48(1):69-82
[129]D. Zeng and K. Syeara. Bayesian learning in negotiation. International Journal of Humman Computer Studies, 1998, 48(1):125-141
[130]Guangzhu Chen, Zhishu Li, Daohua Yuan; A model of multi-agent system based on immune evolution. Advanced Information Networking and Applications, 19th International Conference on. 2005, 1(5):53-58
[131]Weihong Zhang, Qiang Ji. A factorization approach to evaluating simultaneous influence diagrams. Systems, Man and Cybernetics, Part A, IEEE Transactions on. 2006, 36(4):746-757
[132]Shiliang Sun, Changshui Zhang, Guoqiang Yu. A bayesian network approach to traffic flow forecasting. Intelligent Transportation Systems, IEEE Transactions on. 2006,7(1):124-132
[133]Brennan R W, Fletcher M, Norrie D H. An Agent-based approach to reeonfiguration of real-time distributed control systems [J]. IEEE Transactions on Robotics and Automation, 2002, 18(4):444-451
[134]Abbas, A.E.; Entropy methods for joint distributions in decision analysis. Engineering Management, IEEE Transactions on. 2006, 53(1): 146-159
[135]White, C.C., Ⅲ; A survey on the integration of decision analysis and expert systems for decision support. Systems, Man and Cybernetics, IEEE Transactions on. 1990,20(2):358-364
[136]Qiang Ji; Lan, P.; Looney, C.;A prohabilistic framework for modeling and real-time monitoring human fatigue. Systems, Man and Cybernetics, Part A, IEEE Transactions on, 2006,36(5):862-875
[137]Naphide, H.R.; Huang, T.S.; A probabilistic framework for semantic video indexing, filtering, and retrieval. Multimedia, IEEE Transactions on, 2001,3(1): 141-151
[138]Friedman, N.,Murphy. Learning the Structure of Dynamic Probabilistic Networks, Proc. UAI, 1998:139-147.
[139]S.Dupont, J.Luettin. Audio-visual speech modeling for continuous speech recognition. IEEE Trans. Multimedia, 2000, 2(3): 141-151
[140]E.Casto,J.M.Gutierrez, A.S.Hadi. Expert Systems and Probabilistic Network Models. Springer Verlag, New York, 1997
[141]Diamantini, C.; Potena, D.; Panti, M.; Developing an open knowledge discovery support system for a network environment. Collaborative Technologies and Systems, 2005. Proceedings of the 2005 International Symposium on. 2005,5:274-281
[142]衡星辰，覃征，邵利平．动态贝叶斯网络在复杂系统中建模方法的研究．系统仿真学报，2006，8(4)：1002-1005
[2]Kumar, B.R.; Shanmugam, J.; Janarthanan, S.;Development of expert system for the design of airborne equipment. Digital Avionics Systems Conference, 2004. The 23rd.2004,2:24-28
[3]Yan-Qing Zhang; Constructive granular systems with universal approximation and fast knowledge discovery. Fuzzy Systems, IEEE Transactions on. 2005, 13(1):48-57
[4]Melby, N.J.; Comparative relative strength in artificial immune systems: system wellness. Southeast Con, 2005. Proceedings. IEEE. 2005,4:368-371
[5]Yang BS. Optimum design of short journal bearings by artificial life algorithm. Tribology, 2001,34(7):427-435
[6]Shichun Mei etc. An Adaptive Digital Watermarking Algorithm Based on Neural Network. Communication Fournal,2002,23(12):47-53
[7]Shaout A, Scharboneau J. Fuzzy Logic Based Modification System for the Learning Rate in Back propagation. Computers and Electrical Engineering,2000, 26(2): 125-139
[8]Yeung, D.S.; Degang Chen; Tsang, E.C.C.; On the generalization of fuzzy rough sets. Fuzzy Systems, IEEE Transactions on. 2005,13(3):343-361
[9]Tchignirinskaia L, Lu S, Molz F J, et al. Multifractal Versus Monofractal Analysis of Wetland Topography. Stochastic Environmental Research and Risk Assessment, 2000,(14):8-32
[10]Amigoni, F.;,Beda, A.;,Gatti, N.. Combining rate-adaptive cardiac pacing algorithms via multiagent negotiation. Information Technology in Biomedicine, IEEE Transactions on. 2006,10(1):11-18
[11]Pearl J.Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference[M].Morgan Kaufmann, Inc.San Mateo,CA 1988:185-189
[12]K. Hu, Y. Lu, C. Shi, Incremental Association Rule Mining: A Concept Lattice Approach.In: Ning Z, Lizhu Z. Eds. Proc. of PAKDD-99. Springer, 1999:109-113
[13]Ferguson, ThomasS. Development of the decision model of On the History of Statistics and Probability. Donald B.Owenr,1976:335-346
[14]N. Oliver, B. Rosario. A Bayesian computer vision system for modeling human interactions. IEEE Trans. Pattern Anal. Mach. Intell. 2000,22(8):831-843
[15]宋志伟，陈小平．仿真机器人足球中的强化学习．机器人，2003，25(7)：761-766
[16]R.A.Howard and J.E.Matheson. Influence diagrams. In R.A.Howard, Readings on the Principles and Applications of Decision Analysis. 1981,2:719-792
[17]Madsen, A.L. and D.Nilsson. Solving influence diagrams using HUGIN, Shafer-Shenoy and Lazy propagation. Uncertainty in Artificial Intelligence, 2001,17:337-345
[18]B.Banerjee,A.Bisjee,A.Biswas. Using Bayesian Netoworks to Model Agent Relationships. Applied Artif. Intelligence Journal. 2000,14(9):867-880
[19]S.Noh and P.J.Gmytrasiewicz. Agent modeling in antiarir defense. In Proceedings of the Sixth International Conference on User Modeling. 1997,6:389-400
[20]Kal Virtanen, Tuomas Ralvio. An Influence Diagram Approach to One-on-One Air Combat. 10th on Dynamic Games and Applications (ISDG2002), Russia. 2002, 7:12-15
[21]Mauricio Marengoni. Decision Making and Uncertainty Management in a 3D Reconstruction System. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003,25(7) 852-858
[22]Shenoy. Valuation_based systems for Bayesian decision analysis.Operations Research, 1992, 40:463-84
[23]D.Koller and B.Milch. Multi-agent influence diagrams for representing and solving games. In IJCAI-01,2001:1027-1036
[24]Avi Pfeffer, Ya'akov Gal. A Language for Descriptive Decision and Game Theory. AAMAS 2003, Melbourne, Victoria, Australia, Proceedings. ACM 2003:265-272
[25]Chung-Lin Huang; Huang-Chia Shih; Chung-Yuan Chao. Semantic analysis of soccer video using dynamic Bayesian network. Multimedia, IEEE Transactions on. 2006,8(4):749-760
[26]Ghahramani,Z. An introduction to Hidden Markov models and Bayesian Network. Int. Journal of pattern Recognition and Artificial Intelligence, 2001, 15(1):39-43
[27]Zweig, G.G. Speech Recognition with Dynamic Bayesian Networks. Ph.D.thesis, University of California, Berkeley.
[28]方帅，薛方正，徐心和．基于背景建模的动态目标检测算法的研究与仿真．系统仿真学报．2005，17(1)：159-161
[29]Kim SY, Imoto S,Miyano S.Inferring gene networks from time series microarray data using dynamic Bayesian networks.Brief Bioinform 2003;4:228-235
[30]D.Koller and R.Parr.Computing factored value functions for policies in structured MDPs.In IJCAI-99, 1999:1332-1339
[31]M.T.J.Spaan and F.C.A.Groen. Team coordination among robotic soccer players. In G.Kaminka, P.U.Lima, editors,Robocup2002. Spring-Verlag
[32]C.Boutilier. Sequential optimality and coordination in multi-agent systems. In IJCAI-99, 1999:478-485
[33]王红卫，李琛，刘会新．马尔可夫决策过程复杂性的熵测度．控制与决策，2004，19(9)：983-987
[34]Mauricio Marengoni. Decision Making and Uncertainty Management in a 3D Reconstruction System IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(7):852-858
[35]Barto, A. O., and Mahadevan. Recent Advances in Hierarchical Reinforcement Learning. Discrete Event Dynamic Systems. Theory and Applications, 2003, 13 (1/2):41-77
[36]P.Dagum and M.Luby, Approximating probabilistic inference using Bayesian networks is NP-hard,Artificial Intelligence.60(1), 1993:141-153
[37]F.R.BACH, M.I.JORDAN. Tin junction trees. In T. G. Dietterich, S.Becher, editors. Advances in Neural Information Processing Systems, 2002:569-576.
[38]S.Kirshner, P.Smyth. Conditional Chow-Liu tree structures for modeling discrete-valued vector time series. Technical. Report 04-04,School of information and computer Science, University of California, Irvine, 2004
[39]M.A.Paskin. Thin junction tree filters frontier for simultaneous localization and mapping. In Proc. Of IJCAI-03,2003:1157-1164.
[40]U.FEIGE,M.Hajiaghayi. Improved approximation algorithms for minimum-weight verter separators, in Proc. the 37th ACM Symposium on Theory of Computing, 2005.5:563-572
[41]Pedro Larranaga,Cindy M.H.Kuijpers. Decomposing Bayesian networks: triangulation of the moral graph with genetic algorithms Statistics and Computing 1997:19-34
[42]A.Beygelzimer and I.Rish. Inference complexity as a model-section criterion for learning Bayesian nwtworks. In Proceedings of the Eighth International Conference on Principles of Knowledge Representation and Reasoning(KR2002),Toulouse,France,2002
[43]F.V.Jensen, A.L.Madsen, LAZY propagation. A junction tree inference algorithm based on lazy evaluation. Artificial Intelligence. 1999,(113): 203-245
[44]D.Draper. Clustering without triangulation. Proc.UAI-95,1995:125-133
[45]K.Murphy and Y.Weiss. The factored frontier algorithm for approximate inference in DBNs. In Proc. Of UAI-01,2001:378-385
[46]周本达，王浩，姚宏亮．1 1／2片联合树算法在动态贝叶斯网精确推理中的应用．计算机工程与应用，2005，41(14)：81-84
[47]X.Boyen and D.Kollen. Tractable inference for complex stochastic processes. In Proc. Of UAI-98,1998:33-42
[48]K.Murphy and Y.Weiss. The factored frontier algorithm for approximate inference in DBNs. In Proc. Of UAI-01,2001:378-385
[49]M.A.Paskin. Thin junction tree filters for simultaneous localization and mapping. In proc. Of IJCAI-03,2003:1157-1164
[50]S.Arulampalam, S.Maskell,N. Gordon. A tutorial on particle filters for on-line non-linear/non Gaussian Bayesian tracking. IEEE Tran. On Signal Processing,2002,50(2):174-188
[51]A.Doucet. N.de Freitas, K.Murphy. Rao-blackwellised particle filtering for dynamic Bayesian networks. In Proceedings of the UAI-16th, 2000:253-259
[52]NG.B.,Pfeffer, A.,Dearden, R., and Hutter. Factored sampling for monitoring nonlinear hybrid systems with autonomous transitions. Submitted to the Conference on Uncertainty in Artificial Intellingence,2004.
[53]Wooldridge M J, Jennings N R. Intelligent agent: theory and practice [J]. Knowledge Engineering Review, 1995,10(2): 115-152
[54]Burkhard, H.D.; Duhaut, D.; Fujita, M.; Lima, P.; The road to RoboCup 2050[J]. Robotics & Automation Magazine, IEEE. 2002,9(2):31-38
[55]Dicky Suryadi and Piotr J.Gmytrasiewicz. Learning Models of Agents Using Influence Diagrams. IJCAI-99, 1999.8
[56]Scherrer, B.; Charpillet, F.; Cooperative co-learning: a model-based approach for solving multi-agent reinforcement problems Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings. 14th IEEE International Conference on. 2002, (10):463-468
[57]C.Guestrin, D Koller. Context-specific multiagent coordination and planning with factored MDPs. In AAAI 8th Nation conf on Artificial Intellingence, 2002,07:253-259
[58]王骋，王浩，方宝富．使用基于值规则的协作图实现多agent的动作选择．计算机工程与应用，2004，40(19)：61-62
[59]薛方正，方帅，徐心和．基于离散变量动作空间的多移动机器人对抗策略系统．东北大学 学报，2004，12：1138-1141
[60]THOMAS D.NIELSENi, FINN V. Learning a decision maker's utility function from (possibly) inconsistent behavior. Artificial Intelligence, 2004,160:53-78
[61]Sandholm T, Lesser V. Coalition among computationally bounded agents [J]. Artificial Intelligence, 1997,94(1): 99-137
[62]Zlotkin, G, Rosenschein J S. Domain theory for task oriented negotiation. Proceedings of the 13th International Joint Conference on Artificial Intelligence[C]. Morgan Kaufmann Publ Inc, 1993,416-422
[63]R.A.HOWARD and J.E.MATHESON. Influence diagrams[R]. Readings on the Principles and Applications of Decision Analysis. 1984:719-792.
[64]A.P. DAWLD. Influence Diagrams for Causal Modeling and Inference[J]. International Statistical Review, 2002,70(2):161-189.
[65]CHARNES and SHENOY. Multistage Monte Carlo Method for Solving Influence Diagrams[J]. Management Science. 2004,50(3):405-418
[66]D.HECKERMAN, D.GEIGER. Learning Bayesian networks: the combination of knowledge and statistical data[J]. Machine Leaning. 1995, 20(3): 197-243
[67]U.CHAJEWSKA, D.KOLLER. Utilities as random variables: density estimation and structure discovery[C], Proceedings of the Sixteenth Conference on Uncertainty in Artificeal Intelligence, Stanford,CA. 2000:63-71
[68]P.LARRANAGA, C.KUIJPERS. Learning Bayesian Network Structures by Searching for the Best Ordering with Genetic Algorithms[J],IEE Tons, Systems,Man,and Cybernetics, 1996,26(4):487-493
[69]王双成，苑森淼．具有丢失数据的贝叶斯网络结构学习研究[J]．软件学报，2004，15(7)：1042-1048
[70]XIAO-LIN Li, SEN-MIAO YUAN. Learning Bayesian Networks Structures based on extending evolutionary programming. Pro. Of the Third international conference on Machine Learning and Cybernetics, 2004:26-29
[71]Nir Friedman. The Bayesian structural EM algorithm. In Uncertuinty in Artificial Intelligence: Proceedings of the Fourteenth Conference(UAI),1998, 129-138
[72]LIU DY, WANG F, LU YN et.al.. Research on learning Bayesian network structure based on genetic algorithm[J]. Journal of Computer Research and Development, 2001,38(8):916-922
[73]P.TURNER, G. MONTAGUE. Nonlinear and direction-dependent dynamic process modeling using neural networks[C]. IEEE Proc. Control Theory Appl, 1996, 143(1):44-48
[74]A.S.D'AVIILA GARCEZ, K.BRODA. Neural-Symbolic Learning Systems: Foundations and Applications. Perspectives in Neural Computing. Springer-Verlag, 2002
[75]K.Murphy.The hayes net toolbox for matlab. Computing Science aad Statistics, 2001,33:331-351
[76]D.Koller. and B. Milch. Multi-agent influence diagrams for representing and solving games[C]. In IJCAI., 2001: 1024-1034
[77]Y.Gal and A.Pfeffer. A language for modeling Agents decision making processes in games[C]. In Proc. AAMAS-2nd, 2003
[78]Zhong-Yu Zhang, Wei-Yu Liu, Wei-Hua Li. Dynamic multi-gem influence diagrams for modeling multistage games[C]. Proc. 2002 International Conference on Machine Learning and Cybernetics, 2002:1184-1188
[79]Hongliang Yao, Hao Wang, Yousheng, Zhang,Junzhao Li. An Extensional Junction Tree Approximate Inference Algorithm for Dynamic Influence Diagrams. IEEE Proceedings of 2005 International Conference on Neural Networks. 2005,10:396-400
[80]Yao Hongliang, Wang Hao, ZhangYouSheng.Simplifying Computation of Dynamic Influence Diagrams. IEEE the Third International Conference on Machine Learning and Cybenetics ,Shanghai.2004, 8:59-62
[81]王浩．基于影响图的多Agent决策问题研究．合肥工业大学学报，2005，28(9)：1112-1116
[82]P.Dagum and M.Luby, Approximating probabilistic inference using Bayesian networks is NP-hard,Artificial Intelligence[J]. 1993, 60(1): 141-153
[83]田凤占，张宏伟，陆玉昌，石纯一．多模块贝叶斯网络中推理的简化[J]．计算机研究与发展，2003，40(8)：1230-1237
[84]U.Kjaerulff. Reduction of computational complexity in Bayesian networks through removal of weak dependences. In UAI-94, 1994:374-382
[85]Rached, Z., Alajaji, F., Campbell, L.L.. The Kullback-Leibler divergence rate between Matkov sources Information Theory, IEEE Transactions on. 2004, 50(5):917-921
[86]Shenoy, p.p ,"Valuation_based systems for Bayesian decision analysis." Operations Research, 1992,40:63-84
[87]Madsen,A.L. Lazy propagation:A junction tree inference algorithm based on lazy evaluation. Artificial Intelligence, 1999, 113:203-245.
[88]Nilsson, D. and Lauritzen, S.. Evaluating influence diagrams using LIMIDs. In Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann, Stanford, California. 2000:436-450
[89]William B. Davis. Graphical Model Theory for Wireless Sensor Networks. Lawrence Berkeley National Laboratory. Paper LBNL-53452 December8, 2002
[90]U. Kjaerulff, Optimal decomposition of probabilistic networks by simulated annealing,Stat.and compu. 1992(2):7-17
[91]Pedro Larranaga, Cindy M.H.Kuijpers,Mikel Poza and Robertoh.Murga Decomposing Bayesian networks:triangulation of the moral graph with genetic algorithms Statistics and Computing, 1997:19-34
[92]Wittig T, ed. ARCHON: An Architecture for multiagent systems [M]. Ellis Horwood, Chichester, United Kingdom, 1992
[93]Jennings N R, Mamdani E H, Corera J M, et al. Using Archon to develop real-world DAI applications[J]. IEEE Intelligent Systems and Their Applications, 1996, 11(6): 64-70
[94]P.Larranaga, C.Kuijpers,R.Murga, and Y.Yurramendi. Learning Bayesian Network Structures by Searching for the Best Ordering with Genetic Algorithms.IEEE Trans,Systems,Man, and Cybernetics, 1996,26(4):487-493
[95]Josep Roure,Ramon Sanguesa. Incremental Methods for Bayesian Network Learning, September 20,1999.
[96]B.Banerjee,A.Bisjee,A.Biswas. Using Bayesian Netoworks to Model Agent Relationships. Applied Artif. Intelligence Journal, 2000, 14(9):867-880
[97]M.Kearns, M.Littman. Graphical models for game theory. In UAI, 2001:253-260
[98]Boutilier C, Dearden R, Goldszmidt M. Stochastic dynamic programming with factored representations. Artificial Intelligence,2000,121(1-2):49-107
[99]Fengzhan Tian and Yuchang Lu. A DBN inference algorithm using junction tree. In Proc of the 5 world congress on intelligent control and Automation, 2004, 6:4236-4240
[100]R.Dechter.Bucket elimination: A unifying framework for probabilistic inference. In Proceedings of the Twelfth Conference on Uncertainty in Articial Intelligence(UAI-96), 1996
[101]N de Freitas. Rao-Blackwellised particle filtering for fault diagnosis. IEEE Aerospace, 2002,4:1767-1772
[102]A Doucet. On sequential simulation-based methods for Bayesian filtering, Department of Engineering, Cambridge University, Technical report CUED/F-INFENG/TR.310,1998
[103]D Fox. KLD-sampling: Adaptive particle filters. Advances in Neural Information Processing Systems 14 (NIPS), 2001
[104]Rached, Z.; Alajaji, F.; Campbell, L.L.; The Kullback-Leibler divergence rate between Markov sources Information Theory[J]. IEEE Transactions on, 2004, 50(5):917-921
[105]E.Levin.R.Pie Vaccini,and w.Eckert. A Stochastic Model of human-machine Interaction for learning processing. 2000, 8(1):11-23
[106]M.Asada, E.Uchibe. Cooperative behaviour acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development. Artificial Intelligence. 1999,110:276-292
[107]M.J.Mataric. Reinforcement learning in the multi-robot domain. Autonomous Robots, 1997,4:77-83
[108]L.locchi,D.Nardi.Distributed coordination in heterogeneous multi-robot systems. Autonomous Robots, 2003,15:155-168.
[109]M.J.Mataric, G.S.Sukhatme. Multi-robot task allocation in uncertain environments. Autonomous Robots, 2003,14:255-263
[110]A.Merkre and M.Riedmiller. A reinforcement learning approach to robotic soccer. In Robocup 2001,2001:435-440
[111]史忠植．智能主体及其应用[M]．北京：科学出版社，2000
[112]蔡自兴，艾真体——分布式人工智能研究的新课题[J]．计算机科学，2002,29(12)：123-126
[113]胡山立，石纯一．一种任意时间联盟结构生成算法[J]．软件学报，2001，12(5)：729-734
[114](美)S Russell，P Norvig著，姜哲，金奕江等人译．人工智能——一种现代方法(第二版)．人民邮电出版社,2003
[115]胡士强，敬忠良．粒子滤波算法综述．控制与决策．2005,20(4)：361-365
[116]张润梅，王浩，姚宏亮，方宝富．一种基于影响图的决策方法及在Robocup中的应用．系统仿真学报，2005,17(1)：134-137
[117]姜卯生，王浩，姚宏亮．朴素贝叶斯分类器增量学习序列算法研究．计算机工程和应用,2004,40(17)：57—59
[118]Vermaak J.Particle methods for Bayesian modeling and enhancement of speech signals [J].IEEE Trans Audo Speech Processing,2002,10(3): 173-185
[119]Guestrin CE, Koller D, Parr R. Efficient solution algorithms for factored MDPs. Journal of Artificial Intelligence Research. 2003,19:399-468
[120]高建清，王浩，于磊，方宝富．一种模糊强化学习算法及其在RoboCup中的应用．计算机工程与应用．2006．42(6)：52-54
[121]MUN Wai Lee, ISAAC Cohen, SOON Ki Jung, Particle filter with analytical inference for human body tracking. IEEE Workshop on Motion and Video Computing. Florida:IEEE, 2002:159-165
[122]于磊，王浩．Robocup中传球策略研究．计算机工程与应用，2004．40(28)：59-69
[123]姚宏亮，王浩，胡学钢，汪荣贵．基于遗传算法和MDL原则的贝叶斯网络结构优化算法．南京大学学报(自然科学版)，2002，38(11)：23-27
[124]姚宏亮，王浩，方宝富，胡学钢．基于影响图和动态贝叶斯网络的多Agent系统 中国人工智能进展，中国人工智能学会第10届全国学术年会．北京邮电大学出版社，2003，11：242-247
[125]汪荣贵，张佑生，王浩．分组样本下先验BN模型及条件概率的学习算法．微电子学与计算机．2002，19(5)：1-3
[126]H.H.Bui,D.H.Kieronska, and S.Venkatesh. Learning other agent" prefercenees in multiagent negotiation. in :Proc. of the 13th Nat. conf. on Artif. Intell.,Cambridge, 1996:114-119
[127]S.Sen and M.Sekaran. Individual learning of coordination knowledge, Journal of Experimental Theoretical Artificial lntelligence, 1998,10:333-356
[128]S.Sen,N.Arora, S.Roychowdhury. Using limited information to enhance group stability.International Jorunal of Human_Computer Studies, 1998, 48(1):69-82
[129]D. Zeng and K. Syeara. Bayesian learning in negotiation. International Journal of Humman Computer Studies, 1998, 48(1):125-141
[130]Guangzhu Chen, Zhishu Li, Daohua Yuan; A model of multi-agent system based on immune evolution. Advanced Information Networking and Applications, 19th International Conference on. 2005, 1(5):53-58
[131]Weihong Zhang, Qiang Ji. A factorization approach to evaluating simultaneous influence diagrams. Systems, Man and Cybernetics, Part A, IEEE Transactions on. 2006, 36(4):746-757
[132]Shiliang Sun, Changshui Zhang, Guoqiang Yu. A bayesian network approach to traffic flow forecasting. Intelligent Transportation Systems, IEEE Transactions on. 2006,7(1):124-132
[133]Brennan R W, Fletcher M, Norrie D H. An Agent-based approach to reeonfiguration of real-time distributed control systems [J]. IEEE Transactions on Robotics and Automation, 2002, 18(4):444-451
[134]Abbas, A.E.; Entropy methods for joint distributions in decision analysis. Engineering Management, IEEE Transactions on. 2006, 53(1): 146-159
[135]White, C.C., Ⅲ; A survey on the integration of decision analysis and expert systems for decision support. Systems, Man and Cybernetics, IEEE Transactions on. 1990,20(2):358-364
[136]Qiang Ji; Lan, P.; Looney, C.;A prohabilistic framework for modeling and real-time monitoring human fatigue. Systems, Man and Cybernetics, Part A, IEEE Transactions on, 2006,36(5):862-875
[137]Naphide, H.R.; Huang, T.S.; A probabilistic framework for semantic video indexing, filtering, and retrieval. Multimedia, IEEE Transactions on, 2001,3(1): 141-151
[138]Friedman, N.,Murphy. Learning the Structure of Dynamic Probabilistic Networks, Proc. UAI, 1998:139-147.
[139]S.Dupont, J.Luettin. Audio-visual speech modeling for continuous speech recognition. IEEE Trans. Multimedia, 2000, 2(3): 141-151
[140]E.Casto,J.M.Gutierrez, A.S.Hadi. Expert Systems and Probabilistic Network Models. Springer Verlag, New York, 1997
[141]Diamantini, C.; Potena, D.; Panti, M.; Developing an open knowledge discovery support system for a network environment. Collaborative Technologies and Systems, 2005. Proceedings of the 2005 International Symposium on. 2005,5:274-281
[142]衡星辰，覃征，邵利平．动态贝叶斯网络在复杂系统中建模方法的研究．系统仿真学报，2006，8(4)：1002-1005