Learning in Stackelberg Games with Non-myopic Agents (via Zoom)
Abstract: We study Stackelberg games where a principal repeatedly interacts with a long-lived, non-myopic agent, without knowing the agent's payoff function. Although learning in Stackelberg games is well-understood for myopic agents, non-myopic agents pose additional challenges since they may select inferior actions in the present to mislead the principal. We provide a general framework reducing learning in this setting to robust bandit optimization with myopic agents. To apply this, we design minimally reactive bandit algorithms for security games, demand learning, strategic classification, and finite Stackelberg games. Along the way, we improve the state-of-the-art query complexity of learning security games from O(n^3) to a near-optimal O(n log n).
Bio: Sloan Nietert is a fourth-year PhD student in Computer Science at Cornell University, where he is advised by Ziv Goldfeld. His research interests include learning theory, algorithms, and statistics in high dimensions, with a particular focus on optimal transport. His honors include an NSF Graduate Research Fellowship, a Fulbright U.S. Student Grant with the Alfréd Rényi Institute of Mathematics, and the Outstanding Senior in Science award from Clemson University.