Online Learning against Strategic Adversary.

Our work considers repeated games in which one player has a different objective than others. In particular, we investigate repeated two-player zero-sum games where the column player not only aims to minimize her regret but also stabilize the actions. Suppose that while repeatedly playing this game, the row player chooses her strategy at each round by using a no-regret algorithm to minimize her regret. We develop a no-dynamic regret algorithm for the column player to exhibit last round convergence to a minimax equilibrium. We show that our algorithm is efficient against a large set of popular no-regret algorithms the row player can use, including the multiplicative weights update algorithm, general follow-the-regularized-leader and any no-regret algorithms satisfy a property so called "stability''. Our algorithm can be applied to the game setting where the column player is also a designer of the system, and has full control over payoff matrices.