2026
Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations
AAAI 2026technical
We present a novel framework for online learning in Stackelberg general-sum games, where two agents, the leader and follower, engage in sequential turn-based interactions. At the core of this approach is a learned diffeomorphism that maps the joint action space to a smooth spherical Riemannian manif