Reviews: Strategizing against No-regret Learners

This paper asks how a player should exploit knowledge that their opponent in a repeated game is using a no-regret learning algorithm. Prior work has studied this question in Bayesian settings, such as when the learning player is a buyer and the rational player is a seller. This question extends the ideas to a non-Bayesian setting. In general, the rational player can guarantee the first-mover Stackelberg utility in the game. That is, being rational against a no-regret learner is worth at least as much as going first in a Stackelberg game.