Metraipolis › archive › dc_2addceb6767e
Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage — arXiv:2610.04997
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04997
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:30:50.792Z
- SHA-256 of the archived text
f6806cfa07e9882409ae103a423aa715a19a1ab425cbb545ee20bb2e270956b0- Stable URL of this page
https://metraipolis.com/documento/dc_2addceb6767e
How to cite
Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage — arXiv:2610.04997 — arXiv, https://arxiv.org/abs/2610.04997 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2addceb6767e (Metraipolis archive dc_2addceb6767e, sha256 f6806cfa07e9882409ae103a423aa715a19a1ab425cbb545ee20bb2e270956b0)
BibTeX
@misc{dc2addceb6767e,
title = {Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage — arXiv:2610.04997},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04997},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2addceb6767e; sha256 f6806cfa07e9882409ae103a423aa715a19a1ab425cbb545ee20bb2e270956b0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04997. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions and negotiations with private valuations. We introduce unilateral prescriptive concentrability and show that asymmetric information can change offline coverage through its effect on equilibrium behavior. For finite state-action spaces, we develop a pessimistic algorithm with an $\tilde{O}(1/\sqrt{n})$ exploitability rate, matching the standard sample-size dependence for fully observed minimax games. We further develop a pessimistic policy mirror descent framework, PPA-PMD, for general function approximation and obtain a unified $\tilde{O}(1/\sqrt{n} + 1/\sqrt{T})$ exploitability rate with no-regret actor updates. Together, these results provide the first theoretical framework for offline equilibrium learning under public-private information constraints.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04997 — 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 2026-10-06T05:27:05.754Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).