Learning across games

TL;DR: It is demonstrated that there are learning spillovers across games but participants learn to play strategically equivalent games in the same way.

TL;DR: In this paper, the authors describe a series of laboratory experiments that implement specific examples of a general network structure, where actions are either strategic substitutes or strategic complements, and participants have either complete or incomplete information about the structure of a random network.

TL;DR: The existence of a bifurcation in the dynamics of the system is confirmed and three regions for equilibrium selection are identified, one of which does not appear in common one- and two-population models.

TL;DR: In this paper, the standard framework for analyzing games with incomplete information models players as if they have an innite depth of reasoning, and generalizes the type to games with complete information.

TL;DR: A review of continuous time models can be found in this paper, where the authors present an algorithm for the Ergodic Cost Problem: Formulation and Algorithms 7.1 Formulation of the control problem 7.2 A Jacobi Type Iteration 7.3 Approximation in Policy Space 7.4 Numerical Methods 7.5 The Control Problem 7.6 The Interpolated Process 7.7 Computations 7.8 Linear Programming 7.

TL;DR: The juxtaposition of these two expressions in the title reflects the ambition of the authors to produce a reference work, both for engineers who use adaptive algorithms and for probabilists or statisticians who would like to study stochastic approximations in terms of problems arising from real applications.

TL;DR: In this article, the ex ante predictive power of reinforcement learning models and their ex ante descriptive power was investigated in all experiments we could locate involving 100 periods or more of games with a unique equilibrium in mixed strategies.

TL;DR: In this article, the authors use simple learning models to track the behavior observed in experiments concerning three extensive form games with similar perfect equilibria, and they argue that for predicting observed behavior the intermediate term predictions of dynamic learning models may be even more important than their asymptotic properties.