Learning in Games

28 Apr 2009 07:11

---

See also Collective Cognition; Evolutionary Economics; Machine Learning, Statistical Inference and Induction; the Minority Game; Sequential Decisions Under Uncertainty; Universal Prediction Algorithms

Recommended:
• Jenna Bednar and Scott Page, "Games Theory and Culture" [PDF]
• Nicolo Cesa-Bianchi and Gabor Lugosi, Prediction, Learning, and Games [Mini-review]
• Dean P. Foster and H. Peyton Young, "Learning, hypothesis testing, and Nash equilibrium," Games and Economic Behavior 45 (2003): 73--96 [pdf]
• Herbert Gintis, Game Theory Evolving: A Problem-Centered Introduction to Modeling Strategic Interaction
• Ariel Rubinstein, Modeling Bounded Rationality [Review: O docta simplicitas!]
• José M. Vidal and Edmund H. Durfee, "Predicting the Expected Behavior of Agents That Learn About Agents: The CLRI Framework," cs.MA/0001008
• H. Peyton Young, Individual Strategy and Social Structure: An Evolutionary Theory of Institutions [Review: A Myopic (and Sometimes Blind) Eye on the Main Chance, or, the Origins of Custom]

To read:
• Jacob Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin, "A Stochastic View of Optimal Regret through Minimax Duality", arxiv:0903.5328
• James Bergin and Barton L. Lipman, 1996, "Evolution with State-Dependent Mutations," Econometrica 64 (1996): 943--956
• Andreas Blume, "A Learning-Efficiency Explanation of Structure in Language", Theory and Decision 57 (2004): 265--285
• Lawrence E. Blume and David Easley
  • "If You're So Smart, Why Aren't You Rich? Belief Selection in Complete and Incomplete Markets," SFI Working Paper 01-06-031
  • "Optimality and Natural Selection in Markets," SFI Working Paper 98-09-0 82
• Oliver Board, "Dynamic interactive epistemology", Games and Economic Behavior 49 (2004): 49--80
• Christophe Chamley, Rational Herds: Economic Models of Social Learning
• Emilio De Santis and Carlo Marinelli, "Stochastic games with infinitely many interacting agents", math.PR/0505608 [Sounds very cool: "study a class of infinite-horizon non-zero-sum non-cooperative stochastic games with infinitely many interacting agents using ideas of statistical mechanics.... in the general case of asymmetric interactions, the existence of a strategy that allows any player to eliminate losses after a finite random time. In the special case of symmetric interactions ... as time goes to infinity, the game converges to a Nash equilibrium. Moreover, assuming that all agents adopt the same strategy, using arguments related to those leading to perfect simulation algorithms, spatial mixing and ergodicity are proved ... ergodicity [implies] ``fixation'', i.e. that players will adopt a constant strategy after a finite time. ... related to zero-temperature Glauber dynamics on random graphs of possibly infinite volume."]
• Pradeep Dubey and Ori Haimanko, "Learning with Perfect Information", Games and Economic Behavior 46 (2004): 304--324
• Jim Engle-Warnick, William J. McCausland and John H. Miller, "The Ghost in the Machine: Inferring Machine-Based Strategies from Observed Behavior" [i.e., inferring stochastic transducers from data; hence the inclusion here]
• Anders Eriksson and Kristian Lindgren, "A simple model of cognitive processing in repeated games", q-bio.PE/0608015
• Fudenberg and Levine, The Theory of Learning in Games
• Douglas Gale and Hamid Sabourian, "Complexity and Competition", Econometrica 73 (2005): 739--769 ["Extensive-form market games typically have a large number of noncompetitive equilibria. In this paper, we argue that the complexity of noncompetitive behavior provides a justification for competitive equilibrium in the sense that if rational agents have an aversion to complexity (at the margin), then maximizing behavior will result in simple behavioral rules and hence in a competitive outcome. For this purpose, we use a class of extensive-form dynamic matching and bargaining games with a finite number of agents. In particular, we consider markets with heterogeneous buyers and sellers and deterministic, exogenous, sequential matching rules, although the results can be extended to other matching processes. If the complexity costs of implementing strategies enter players' preferences lexicographically with the standard payoff, then every equilibrium strategy profile induces a competitive outcome."]
• Val E. Lambson and Daniel A. Probst, "Learning by Matching Patterns", Games and Economic Behavior 46 (2004): 398--409
• Jacek Miekisz
  • "Statistical mechanics of spatial evolutionary games", cond-mat/0210094
  • "Stochastic stability in spatial games", cond-mat/0409647 = Journal of Statistical Physics 117 (2004): 99--110
  • "Long-run behavior of games with many players", cond-mat/0409742
• Gillies Pagès, "A two armed bandit type problem revisited", math.PR/0502182
• Liviu Panait, Karl Tuyls, Sean Luke, "Theoretical Advantages of Lenient Learners: An Evolutionary Game Theoretic Perspective", Journal of Machine Learning Research 9 (2008): 423--457
• Larry Samuelson (no relation of the Samuelson), Evolutionary Games and Equilibrium Selection
• Mark Stegeman and Paul Rhode, "Stochastic Darwinian equilibria in small and large populations", Games and Economic Behavior 49 (2004): 171--214
• José M. Vidal, Computational Agents That Learn About Agents: Algorithms for Their Design and a Predictive Theory of Their Behavior [Ph.D. thesis, U. Michigan, 1998; on-line]