Metraipolis › archive › dc_c0e91084bbb2

Constant regret in general games via higher-order optimism — arXiv:2609.04113

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04113
License (as archived)
CC0-1.0
Archived
2026-10-17T02:00:21.066Z
SHA-256 of the archived text
42a63da747dfcc96674a8ae83a402813ffde9f2903bb62d46953bddce3060889
Stable URL of this page
https://metraipolis.com/documento/dc_c0e91084bbb2

How to cite

Constant regret in general games via higher-order optimism — arXiv:2609.04113 — arXiv (en), https://arxiv.org/abs/2609.04113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c0e91084bbb2 (Metraipolis archive dc_c0e91084bbb2, sha256 42a63da747dfcc96674a8ae83a402813ffde9f2903bb62d46953bddce3060889)
BibTeX
@misc{dcc0e91084bbb2,
  title = {Constant regret in general games via higher-order optimism — arXiv:2609.04113},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04113},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c0e91084bbb2; sha256 42a63da747dfcc96674a8ae83a402813ffde9f2903bb62d46953bddce3060889},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce an uncoupled learning algorithm which, when employed by all players of an arbitrary $N$-player normal form game with up to $K$ actions per player, guarantees $O(N^3\log^2 K)$ individual regret, uniformly over the horizon of play. The proposed algorithm - which we call higher-order optimism with discounting (HOOD) is a variant of optimistic follow-the-regularized-leader (OptFTRL) that combines a discounted $(N+1)$-th order predictor with entropic regularization over a suitable "lifting" of the game's strategy space. This combination of ingredients is purposefully designed to dampen large oscillations of the induced sequence of play in a controlled manner, removing in this way a key stumbling block of previous attempts to achieve constant regret in general games. Our approach bears several striking similarities to the concurrent - and completely independent - work of Liu, Farina, and Ozdaglar ( arXiv:2608.31166 ), who very recently derived an $O(N^{21}\log^{4} K)$ regret bound through the use of higher-order optimism and an exponential moving average estimator.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-04 in cs.GT).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2609.04113 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:13:00.916Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).