AI RESEARCH

Differential Privacy in the Extensive-Form Bandit Problem

arXiv CS.LG

ArXi:2605.05266v1 Announce Type: cross We consider the extensive-form bandit problem, where on each trial the learner (a user coordinated by a server) plays an extensive-form game against an oblivious adversary, observing the information sets it finds itself in as well as the resulting payoff/loss.