number of standard learning algorithms. The learning theories are (unbeknown to subjects) a best response process, fictitious … play, imitation, reinforcement learning, and a trial & error process. We test whether subjects try to influence those … and that all learning algorithms are subject to exploitation with the notable exception of imitation. The experiment was …

number of standard learning algorithms. The learning theories are (unbeknown to subjects) a best response process, fictitious … play, imitation, reinforcement learning, and a trial & error process. We test whether subjects try to influence those … and that all learning algorithms are subject to exploitation with the notable exception of imitation. The experiment was …

Equilibrium notions for games with unawareness in the literature cannot be interpreted as steady-states of a learning … interpreted as steady-state of both a discovery and learning process. …

Recently there has been much theoretical and experimental work on learning in games. However, learning usually means … learning about the strategic behavior of opponents rather than learning about the game as such. In contrast, here we report on …

It is known that there are uncoupled learning heuristics leading to Nash equilibrium in all finite games. Why should … players use such learning heuristics and where could they come from? We show that there is no uncoupled learning heuristic …" or that "could learn itself". Rather, a player has an incentive to strategically teach such a learning opponent in order …

It is known that there are uncoupled learning heuristics leading to Nash equilibrium in all finite games. Why should … players use such learning heuristics and where could they come from? We show that there is no uncoupled learning heuristic … that could "learn itself". Rather, a player has an incentive to strategically teach such a learning opponent in order to …