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 …

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 …

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 …

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 …