婵犵數濮烽弫鍛婃叏閻戣棄鏋侀柟闂寸绾剧粯绻涢幋鐑嗙劯婵炴垶鐟﹂崕鐔兼煏婵炲灝鍔氶柣搴弮濮婃椽宕楅懖鈹垮仦闂佸搫鎳忕划宀勬偩閻戣棄钃熼柕澶涚畱閳ь剛鏁婚弻銊モ攽閸℃侗鈧鏌$€n偆銆掔紒杈ㄥ浮閸┾偓妞ゆ帒瀚壕鍏兼叏濡灝浜归柛鐐垫暬閺岋綁鎮╅悜妯糕偓鍐偣閳ь剟鏁冮埀顒€宓勯梺鍛婄☉鏋ù婊勭矒閺屻劑寮村Δ鈧禍楣冩倵濞堝灝鏋涘褍閰i獮鎴﹀閻橆偅鏂€闁诲函缍嗘禍璺横缚婵犲洦鈷戠紓浣光棨椤忓嫷鍤曢悹铏规磪閹烘绠涢柣妤€鐗冮幏娲⒒閸屾氨澧涚紒瀣浮楠炴牠骞囬鐘殿啎閻庣懓澹婇崰鏍嵁閺嶎厽鐓熼柨婵嗘噹濡茬粯銇勯锝囩畼闁圭懓瀚伴幖褰掓偡閺夎法顔囬梻鍌氬€风欢姘跺焵椤掑倸浠滈柤娲诲灡閺呰埖瀵肩€涙ḿ鍘炬俊銈忕畳濞夋洜鑺遍崸妤佺厪闁搞儯鍔屾慨宥嗩殽閻愭潙娴鐐差儔閹粓宕卞鍡橈紙闂傚倸鍊搁崐椋庣矆娓氣偓楠炴牠顢曚綅閸ヮ剦鏁嶉柣鎰綑閳ь剝鍩栫换婵嬫濞戞艾顣哄銈冨劜瀹€鎼佸蓟濞戔懇鈧箓骞嬪┑鍥╀簮婵犵鍓濊ぐ鍐偋閹捐钃熼柨鐔哄Т缁€鍐煃閸濆嫬鈧悂寮冲Δ鍛拺濞村吋鐟х粔顒€霉濠婂骸澧版俊鍙夊姍楠炴帒螖閳ь剚鍎柣鐔哥矊闁帮絽顕i幎钘夌厸闁告劦浜為敍婊堟煛婢跺﹦澧戦柛鏂跨Ч钘熼柛顐犲劜閻撴稑霉閿濆牜娼愮€规洖鐭傞弻鈩冩媴鐟欏嫬纾抽梺杞扮劍閹瑰洭寮幘缁樻櫢闁跨噦鎷� [闂傚倸鍊搁崐鎼佸磹瀹勬噴褰掑炊椤掍礁鍓銈嗗姧缁犳垿鐛姀銈嗙厓閺夌偞澹嗛崝宥嗐亜閺傚灝顏紒杈ㄦ崌瀹曟帒顫濋钘変壕闁告縿鍎抽惌娆撴煕閺囥劌鐏犵紒鐙€鍨堕弻銊╂偆閸屾稑顏� | 闂傚倸鍊搁崐鎼佸磹閻戣姤鍤勯柤鍝ユ暩娴犳氨绱撻崒娆掑厡缂侇噮鍨跺畷婵單旈崘銊ョ亰闂佸搫鍟悧濠囧磹婵犳碍鐓㈡俊顖欒濡叉悂鏌f惔顔煎籍婵﹨娅g划娆撳箰鎼淬垺瀚抽梻浣虹《閺呮盯宕弶鎴殨闁归棿绀侀崘鈧銈嗘尵閸犳捇宕㈤鍛瘈闁汇垽娼ф禒婊堟煟韫囨梻绠炵€规洘绻傞~婵嬫嚋閻㈤潧骞愰梻浣呵归張顒勩€冮崨顔绢洸闁跨噦鎷�]

    • 博弈学习理论(英文版)/世界博弈论经典
      • 作者:(美)朱·弗登博格//戴维·K.莱文
      • 出版社:世界图书出版公司
      • ISBN:9787519264628
      • 出版日期:2019/08/01
      • 页数:276
    • 售价:23.6
  • 内容大纲

        本书是任何从事学习理论和博弈理论研究或在应用研究中使用演进博弈理论的人的必读书籍。不同于非合作博弈理论中传统的均衡概念所认为的均衡是在博弈的规则和参与人的收益函数都共知的情况下,由理性参与人的分析和自省产生的结果,《博弈学习理论》则认为均衡是并非完全理性的参与人随着时间的推移寻求优化这一过程的长期结果。
  • 作者介绍

  • 目录

      Series Foreword  xi
      Acknowledgments xiii
    1 Introduction
      1.I  Introduction
      1.2  Large Populations and Matching Models
      1.3  Three Common Models of Learning and/or Evolution
      1.4  Cournot Adjustment
      1.5  Analysis of Cournot Dynamics
      1.6  Cournot Process with Lock.In
      1.7  Review of Finite Simultaneous—Move Games
      Appendix:Dynamical Systems and Local Stability
      References
    2 Fictitious Play
      2.1  Introduction
      2.2  Two—Player Fictitious Play
      2.3  Asymptotic Behavior of Fictitious Play
      2.4  Interpretation of Cycles in Fictitious Play
      2.5  Multiplayer Fictitious Play
      2.6  Payoffs in Fictitious Play
      2.7  Consistency and Correlated Equilibrium in Games with Two Strategies
      2.8  Fictitious Play and the Best-Response Dynamic
      2.9  Generalizations of Fictitious Play
      Appendix:Dirichlet Priors and Multinomial Sampling
      References
    3 Replicator Dynamics and Related Deterministic Models of Evolution
      3.1  Introduction
      3.2  Replicator Dynamics in a Homogeneous Population
      3.3  Stability in the Homogeneous—Population Replicator Dynamic
      3.4  Evolutionarily Stable Strategies
      3.5  Asymmetric Replicator Models
      3.6  Interpretation of the Replicator Equation
      3.7  Generalizations of the Replicator Dynamic and Iterated Strict Dominance
      3.8  Myopic Adjustment Dynamics
      3.9  Set-Valued Limit Points and Drift
      3.10  Cheap Talk and the Secret Handshake
      3.11  Discrete.Time Replicator Systems
      Appendix:Liouville’S Theorem
      References
    4 Stochastic Fictitious Play and Mixed—Strategy Equilibria
      4.1  Introduction
      4.2  Notions of Convergence
      4.3  Asymptotic Myopia and Asymptotic Empiricism
      4.4  Randomly Perturbed Payoffs and Smoothed Best Responses
      4.5  Smooth Fictitious Play and Stochastic Approximation
      4.6  PartiaI Sampling
      4.7  Universal Consistency and Smooth Fictitious Play
      4.8  Stimulus—Response and Fictitious Play as Learning Models
      4.9  Learning about Strategy Spaces
      Appendix:Stochastic Approximation Theory
      References

    5 Adiustment Models with Persistent Randomness
      5.1  Introduction
      5.2  Overview of Stochastic Adjustment Models
      5.3  Kandori—Mailath—Rob Model
      5.4  Discussion of Other Dynamics
      5.5  Local Interaction
      5.6  Radius and Coradius of Basins of Attraction
      5.7  Modified Coradius
      5.8  Uniform Random Matching with Heterogeneous Populations
      5.9  Stochastic Replicator Dynamics
      Appendix A:Review of Finite Markov Chains
      Appendix B:Stochastic Stability Analysis
      RefeFences
    6 Extensive。Form Games and Self—confirming Equilibrium
      6.1  Introduction
      6.2  An Example
      6.3  Extensive—Form Games
      6.4  A Simple Learning Model
      6.5  Stability Of Self—confirming Equilibrium
      6.6  Heterogeneous Self-confirming Equilibrium
      6.7  Consistent Self-confirming Equilibrium
      6.8  Consistent Self-confirming Equilibria and Nash Equilibria
      6.9  Rationalizable SCE and Prior Information on Opponents’ Payoffs
      References
    7 Nash Equilibrium,Large Population Models,and Mutations in
      Extensive.Form Games
      7.I  Introduction
      7.2  Relevant Information Sets and Nash Equilibrium
      7.3  Exogenous Experimentation
      7.4  Learning in Games Compared to the Bandit Problem
      7.5  Steady—State Learning
      7.6  Stochastic Adjustment and Backward Induction in a Model of‘Fast Learning’
      7.7  Mutations and Fast Learning in Models of Cheap Talk
      7.8  Experimentation and the Length of the Horizon
      Appendix:Review of Bandit Problems
      References
    8 Sophisticated Learning
      8.1  Introduction
      8.2  Three Paradigms for Conditional Learning
      8.3  Bayesian Approach to Sophisticated Learning
      8.4  Interpreting the Absolute Continuity Condition
      8.5  Choosing among Experts
      8.6  Conditional Learning
      8.7  Discounting
      8.8  Categorization Schemes and Cycles
      8.9  Introspective Classification Rules,Calibration,and Correlated Equilibrium
      8.10  Sonsino’S Model of Pattern Recognition
      8.11  Manipulating Learning Procedures
    References
    Index

同类热销排行榜

推荐书目

  • 孩子你慢慢来/人生三书 华人世界率性犀利的一枝笔,龙应台独家授权《孩子你慢慢来》20周年经典新版。她的《...

  • 时间简史(插图版) 相对论、黑洞、弯曲空间……这些词给我们的感觉是艰深、晦涩、难以理解而且与我们的...

  • 本质(精) 改革开放40年,恰如一部四部曲的年代大戏。技术突变、产品迭代、产业升级、资本对接...

更多>>>