The concentration game: Bayesian updating, regret, and information

arXiv:2608. 18061v1 Announce Type: new Abstract: We give a two-player zero-sum repeated game between a learner and nature whose value identity generates Bayesian updating and an exact accounting of exponential-weights regret at once, and supplies the comparator-class variational form that a wide class of concentration phenomena share.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

• reinforcement-learning