Asuman Ozdaglar

Naively scaling context length in imitation learning is surprisingly robust, challenging previous assumptions about brittleness in policy performance.

Adaptive opponents can significantly alter the landscape of regret minimization, and our new RP-Regret metric reveals how to achieve better cooperative outcomes in repeated games.

Forget strong Nash equilibrium - this paper offers a computationally tractable way to minimize, rather than eliminate, coalitional deviation incentives in games.

Global AI aggregators can actually *worsen* learning compared to specialized, local ones, especially when they update too quickly.

Learning from ranked preferences alone can be surprisingly difficult: even with access to the full ranking of actions, standard online learning guarantees break down unless the environment is sufficiently stable.