Metraipolis › archive › dc_beae2d8836da

Policy Optimization and Statistical Inference for Online Contextual Matrix Games — arXiv:2608.17173

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.17173
License (as archived)
CC0-1.0
Archived
2026-10-18T14:49:03.728Z
SHA-256 of the archived text
656c19ecc78d707b25764bc3268119a2c06add2dfb1f4e427485b678b7cbd913
Stable URL of this page
https://metraipolis.com/documento/dc_beae2d8836da

How to cite

Policy Optimization and Statistical Inference for Online Contextual Matrix Games — arXiv:2608.17173 — arXiv (en), https://arxiv.org/abs/2608.17173 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_beae2d8836da (Metraipolis archive dc_beae2d8836da, sha256 656c19ecc78d707b25764bc3268119a2c06add2dfb1f4e427485b678b7cbd913)
BibTeX
@misc{dcbeae2d8836da,
  title = {Policy Optimization and Statistical Inference for Online Contextual Matrix Games — arXiv:2608.17173},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17173},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_beae2d8836da; sha256 656c19ecc78d707b25764bc3268119a2c06add2dfb1f4e427485b678b7cbd913},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17173. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Online decision making often requires navigating a landscape shaped by both dynamic contexts and strategic interactions. In competitive pricing, for example, hotels must account for both dynamic contextual factors and rivals' strategic responses. Existing approaches address only part of this challenge: contextual bandits optimize single-agent decisions using observable features but ignore multi-player interactions, while online matrix games capture strategic behavior through Nash equilibrium but assume fixed payoffs, ignoring contextual information. How should agents act then when strategic payoffs evolve with contextual signals? We introduce \emph{online contextual matrix games} to integrate contextual information into multi-player online games. We further propose \emph{OnGameLearn}, an online learning algorithm that efficiently balances exploration and exploitation across both player actions and contexts. This approach comes with statistical guarantees: tail bounds for the estimated payoff matrix, the convergence of the estimated Nash equilibrium, the asymptotic normality of the parameter estimators, and the sublinear regret bound. We also develop the notion of \emph{policy value} in matrix games and develop a doubly robust, $\sqrt{T}$-consistent estimator for it. Across simulated studies and a real-world hotel pricing application, we find that OnGameLearn effectively navigates the intertwined challenges of strategic and contextual decision-making.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2608.17173 — 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 2026-10-18T14:47:59.453Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).