Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations

Larkin Liu; Kashif Rasul; Yutong Chao; Jalal Etesami

AAAI 2026technical0 citations

Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations

Larkin Liu, Kashif Rasul, Yutong Chao, Jalal Etesami

Abstract

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 manifold, referred to as the Stackelberg manifold. This mapping, facilitated by neural normalizing flows, ensures the formation of tractable isoplanar subspaces, enabling efficient techniques for online learning. Leveraging the linearity of the agents

BibTeX

@inproceedings{aaai2026_riemannianmanifo,
  title = {Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations},
  author = {Larkin Liu and Kashif Rasul and Yutong Chao and Jalal Etesami},
  booktitle = {AAAI 2026},
  year = {2026}
}