We prove that, in all finite generic extensive-form games of perfect information, a continuous-time best response dynamic always converges to a Nash equilibrium component. We show the robustness of convergence by an approximate best response dynamic: whatever the initial state and an allowed...

This paper studies adaptive learning in extensive form games and provides conditions for convergence points of adaptive learning to be sequential equilibria. Precisely, we present a set of conditions on learning sequences such that an assessment is a sequential equilibrium if and only if there...

This paper aspires to fill a conspicuous gap in the literature regarding learning in games — the absence of empirical verification of learning rules involving pattern recognition. Weighted fictitious play is extended to detect two-period patterns in opponents’ behavior and to comply with the...

Belief models capable of detecting 2- to 5-period patterns in repeated games by matching the current historical context to similar realizations of past play are presented. The models are implemented in a cognitive framework, ACT-R, and vary in how they implement similarity-based categorization...

We introduce the algorithmic learning equations (ALEs), a set of ordinary differential equations which characterizes the finite-time and asymptotic behaviour of the stochastic interaction between state-dependent learning algorithms in dynamic games. Our framework allows for a variety of...

This paper uses a laboratory experiment to study beliefs and their relationship to action and strategy choices in finitely and indefinitely repeated prisoners' dilemma games. We find subjects' beliefs about the other player's action are accurate despite some systematic deviations corresponding...

This paper uses a laboratory experiment to study beliefs and their relationship to action and strategy choices in finitely and indefinitely repeated prisoners' dilemma games. We find subjects' beliefs about the other player's action are accurate despite some systematic deviations corresponding...

Population games describe strategic interactions among large numbers of small, anonymous agents. Behavior in these games is typically modeled dynamically, with agents occasionally receiving opportunities to switch strategies, basing their choices on simple myopic rules called revision protocols...

We choose between alternatives without being fully informed about the rewards from different courses of action. In making our decisions, we use our own past experience and the experience of others. So the ways in which we interact - our social network - can influence our choices. These choices...

We show that for many classes of symmetric two-player games, the simple decision rule "imitate if-better'' can hardly be beaten by any strategy. We provide necessary and sufficient conditions for imitation to be unbeatable in the sense that there is no strategy that can exploit imitation as a...