Learning in Stackelberg Games with Non-myopic Agents

The authors thank the anonymous review team at the 23rd Association for Computing Machinery Conference on Economics & Computation and at Operations Research for their valuable feedback, and they thank Bobby Kleinberg for insightful discussions on robust linear programming, security games, and bandit convex optimization. The authors are grateful to the Simons Institute for the Theory of Computing as part of this work was done during the fall 2022 semester-long program on data-driven decision processes. A two-page abstract of this work appeared at the 23rd Association for Computing Machinery Conference on Economics & Computation.