Metraipolis › archive › dc_ce40b3d5af33
$Q$ Can Play That Game: Online Fitted $Q$-Iteration for Continuous-Action Zero-Sum Markov Games with Convex-Concave Function Approximation — arXiv:2610.04010
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04010
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:23:57.828Z
- SHA-256 of the archived text
02128118a3f208e016f96d6df7bb1f3a087b6a9ad9d13bcaa1c109ca21a59424- Stable URL of this page
https://metraipolis.com/documento/dc_ce40b3d5af33
How to cite
$Q$ Can Play That Game: Online Fitted $Q$-Iteration for Continuous-Action Zero-Sum Markov Games with Convex-Concave Function Approximation — arXiv:2610.04010 — arXiv, https://arxiv.org/abs/2610.04010 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce40b3d5af33 (Metraipolis archive dc_ce40b3d5af33, sha256 02128118a3f208e016f96d6df7bb1f3a087b6a9ad9d13bcaa1c109ca21a59424)
BibTeX
@misc{dcce40b3d5af33,
title = {$Q$ Can Play That Game: Online Fitted $Q$-Iteration for Continuous-Action Zero-Sum Markov Games with Convex-Concave Function Approximation — arXiv:2610.04010},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04010},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce40b3d5af33; sha256 02128118a3f208e016f96d6df7bb1f3a087b6a9ad9d13bcaa1c109ca21a59424},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04010. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Zero-sum Markov games arise in a wide variety of sequential decision-making problems such as adversarial learning and planning against modeled uncertainties. However, prior work on finite-sample guarantees on the learned state-action value function ($Q$-function) for zero-sum Markov games is largely restricted to finite-action settings, or to continuous-action games in which agents have linear dynamics and quadratic rewards (i.e. linear-quadratic, or LQ, games). A central challenge in extending such guarantees to more general continuous-action zero-sum Markov games is that the associated Bellman operator involves a minimax problem that need not admit a tractable saddle-point solution. To this end, we first introduce a class of neural network function approximators for the $Q$-function that is convex-concave in the players' actions, which guarantees that this minimax problem admits a pure-strategy saddle point. We then study an online variant of fitted $Q$-iteration employing this function class and establish, to the best of our knowledge, the first finite-sample guarantees for non-LQ zero-sum Markov games with continuous states and actions. Our code can be found at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2610.04010 — 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 2026-10-06T05:23:50.221Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).