We consider online no-regret learning in unknown games with bandit feedback, where each agent only observes its reward … smooth and strongly monotone games and study optimal no-regret learning therein. Leveraging self-concordant barrier functions … applies this no-regret learning algorithm in strongly monotone games, the joint action converges in \textit{last iterate} to …

While payoff-based learning models are almost exclusively devised for finite action games, where players can test every … action, it is harder to design such learning processes for continuous games. We construct a stochastic learning rule …

In this paper, we discuss learning behavior and the heterogeneity of subjects' ability to perform in real-effort tasks …. Afterwards, we present a novel variant of Erkal et al.'s (2011) encryption real-effort task which aims to minimize learning …-randomization mechanism to minimize learning and heterogeneity. Existing experiments with repeated real-effort tasks find a performance …

Psychologists have long recognized two kinds of learning: one that is relatively shallow and domain-specific; and … recently considered this distinction, and the conditions that stimulate the latter kind of “meaningful” learning in games are … still unclear. Three experiments demonstrate that meaningful learning – the acquisition of the principle of iterated …