Theory of Learning in Games

Name: Theory of Learning in Games
Price: 55.39 USD
Availability: InStock
ISBN: 9780262061940

ISBN-10: 0262061945

ISBN-13: 9780262061940

Edition: 1998

Authors: Drew Fudenberg, David K. Levine

List price: $55.00

30 day, 100% satisfaction guarantee!

Marketplace

2 new & used from $55.39

what's this?

Rush Rewards U
Members Receive:

You have reached 400 XP and carrot coins. That is the daily max!

Description:

Here the authors develop the explanation that equilibrium in games arises as the long-run outcome of a process in which less than fully rational players grope for optimality over time. Ways are suggested for economists to modify traditional concepts.

Book details

List price: $55.00
Copyright year: 1998
Publisher: MIT Press
Publication date: 6/3/1998
Binding: Hardcover
Pages: 294
Size: 6.50" wide x 9.25" long x 1.00" tall
Weight: 1.386

Drew Fudenberg is Professor of Economics at MIT.

David K. Levine is John H. Biggs Distinguished Professor of Economics at Washington University, St. Louis.



Series Foreword


Acknowledgments



Introduction



Introduction



Large Populations and Matching Models



Three Common Models of Learning and/or Evolution



Cournot Adjustment



Analysis of Cournot Dynamics



Cournot Process with Lock-In



Review of Finite Simultaneous-Move Games


Appendix: Dynamical Systems and Local Stability


References



Fictitious Play



Introduction



Two-Player Fictitious Play



Asymptotic Behavior of Fictitious Play



Interpretation of Cycles in Fictitious Play



Multiplayer Fictitious Play



Payoffs in Fictitious Play



Consistency and Correlated Equilibrium in Games with Two Strategies



Fictitious Play and the Best-Response Dynamic



Generalizations of Fictitious Play


Appendix: Dirichlet Priors and Multinomial Sampling


References



Replicator Dynamics and Related Deterministic Models of Evolution



Introduction



Replicator Dynamics in a Homogenous Population



Stability in the Homogenous-Population Replicator Dynamic



Evolutionary Stable Strategies



Asymmetric Replicator Models



Interpretation of the Replicator Equation



Generalizations of the Replicator Dynamic and Iterated Strict Dominance



Myopic Adjustment Dynamics



Set-Valued Limit Points and Drift



Cheap Talk and the Secret Handshake



Discrete-Time Replicator Systems


Appendix: Liouville's Theorem


References



Stochastic Fictitious Play and Mixed-Strategy Equilibria



Introduction



Notions of Convergence



Asymptotic Myopia and Asymptotic Empiricism



Randomly Perturbed Payoffs and Smoothed Best Responses



Smooth Fictitious Play and Stochastic Approximation



Partial Sampling



Universal Consistency and Smooth Fictitious Play



Stimulus-Response and Fictitious Play as Learning Models



Learning about Strategy Spaces


Appendix: Stochastic Approximation Theory


References



Adjustment Models with Persistent Randomness



Introduction



Overview of Stochastic Adjustment Models



Kandori-Mailath-Rob Model



Discussion of Other Dynamics



Local Interaction



Radius and Coradius of Basins of Attraction



Modified Coradius



Uniform Random Matching with Heterogeneous Populations



Stochastic Replicator Dynamics



Review of Finite Markov Chains



Stochastic Stability Analysis


References



Extensive-Form Games and Self-confirming Equilibrium



Introduction



An Example



Extensive-Form Games



A Simple Learning Model



Stability of Self-confirming Equilibrium



Heterogeneous Self-confirming Equilibrium



Consistent Self-confirming Equilibrium



Consistent Self-confirming Equilibria and Nash Equilibria



Rationalizable SCE and Prior Information on Opponents' Payoffs


References



Nash Equilibrium, Large Population Models, and Mutations in Extensive-Form Games



Introduction



Relevant Information Sets and Nash Equilibrium



Exogenous Experimentation



Learning in Games Compared to the Bandit Problem



Steady-State Learning



Stochastic Adjustment and Backward Induction in a Model of "Fast-Learning"



Mutations and Fast Learning in Models of Cheap Talk



Experimentation and the Length of the Horizon


Appendix: Review of Bandit Problems


References



Sophisticated Learning



Introduction



Three Paradigms for Conditional Learning



Bayesian Approach to Sophisticated Learning



Interpreting the Absolute Continuity Condition



Choosing among Experts



Conditional Learning



Discounting



Categorization Schemes and Cycles



Introspective Classification Rules, Calibration, and Correlated Equilibrium



Sonsino's Model of Pattern Recognition



Manipulating Learning Procedures


References


Index