Metraipolis › archive › dc_620cbaa74649

Learning under Opponent Unawareness in Linear-Quadratic Stochastic Games — arXiv:2608.08268

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08268
License (as archived)
CC0-1.0
Archived
2026-10-19T08:55:50.722Z
SHA-256 of the archived text
4049ec6e2c3261b39eb4007d12170cbf5177dd65eeb0c03d04876c096442aaa0
Stable URL of this page
https://metraipolis.com/documento/dc_620cbaa74649

How to cite

Learning under Opponent Unawareness in Linear-Quadratic Stochastic Games — arXiv:2608.08268 — arXiv (en), https://arxiv.org/abs/2608.08268 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_620cbaa74649 (Metraipolis archive dc_620cbaa74649, sha256 4049ec6e2c3261b39eb4007d12170cbf5177dd65eeb0c03d04876c096442aaa0)
BibTeX
@misc{dc620cbaa74649,
  title = {Learning under Opponent Unawareness in Linear-Quadratic Stochastic Games — arXiv:2608.08268},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08268},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_620cbaa74649; sha256 4049ec6e2c3261b39eb4007d12170cbf5177dd65eeb0c03d04876c096442aaa0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08268. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As firms increasingly deploy machine learning for strategic decision-making, understanding algorithmic interactions has become central to operations research and economics. This paper studies learning in infinite-horizon, nonzero-sum linear-quadratic stochastic games under a radically uncoupled information structure, where players are either unaware of opponents or strategically oblivious, observing only a common state and their own action history. Under this minimal information, we analyze an asynchronous decentralized learning process in which each player independently runs a single-agent $\epsilon$-greedy iterated least-squares algorithm. We prove that, despite being unable to identify the system parameters, players' learning dynamics converge almost surely to the complete-information Nash equilibrium and characterize the convergence rate. We then apply the framework to a dynamic Cournot competition with sticky prices. Numerical experiments validate the theoretical results and show that learning under limited information reduces firm profits under both low and high price stickiness, while total surplus declines and market concentration increases when price stickiness is high. Publicly revealing aggregate market output substantially accelerates convergence and mitigates these welfare losses.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-08-11 in cs.GT).
Categorie arXiv: Optimization and Control (math.OC) ; Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG); Theoretical Economics (econ.TH).
Pagina del lavoro: https://arxiv.org/abs/2608.08268 — 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 2026-10-19T08:52:22.705Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).