method · first seen 11 Oct 2026
online mirror descent
Also: OMD
An iterative first-order optimization method that updates policies via mirror maps, used for computing equilibria in games.
Mentions per week
PapersCodeDiscussion
Earliest sources
- DiffNash: Finding Nash Equilibrium in High-Dimensional Continuous Action Spaces with Diffusion PoliciesPapers · 11 Oct 2026 · Haichuan Wang, Anagha Satish, Jiale Zheng, Saisneha Ghatti, Lingkai Kong, Kai Wa…
- A Black-Box Reduction from Regret to Multi-Level CoveragePapers · 9 Nov 2026 · Tuo Liu, Edgar Dobriban, Francesco Orabona
Latest sources
- A Black-Box Reduction from Regret to Multi-Level CoveragePapers · 9 Nov 2026 · Tuo Liu, Edgar Dobriban, Francesco Orabona
- DiffNash: Finding Nash Equilibrium in High-Dimensional Continuous Action Spaces with Diffusion PoliciesPapers · 11 Oct 2026 · Haichuan Wang, Anagha Satish, Jiale Zheng, Saisneha Ghatti, Lingkai Kong, Kai Wa…