动态网络上的去中心化最优均衡学习

View PDF HTML (experimental)

Abstract:This paper studies decentralized learning of socially optimal equilibria in finite normal-form games over dynamic communication networks. Each agent observes only its own realized payoffs, does not know the game a priori, and can communicate only with time-varying neighbors using low-bandwidth messages. We propose networked decentralized optimal equilibrium learning dynamics in which agents generate randomized semantic content/discontent signals from local payoff comparisons and exchange time-stamped time-stacked tables rather than raw actions, payoff information or local estimates/parameters. The method combines table fusion with temporal majority reconstruction to mitigate dynamic communication while preserving fully decentralized operation. We establish finite-time logarithmic regret guarantees, with an in-phase exploration perturbation, for optimal equilibrium selection under utilitarian and proportional-fair social welfare objectives. Simulation results further show that the proposed approach can effectively select socially desirable equilibria over dynamic communication networks.

Comments:	Extended version of S. T. Kiremitci and M. O. Sayin, "Decentralized optimal equilibrium learning over dynamic networks," to appear in the Proceedings of the IEEE Conference on Decision and Control, 2026. It includes an expanded literature review, detailed proofs, and illustrations. This revision (v2) expands the discussion of related work on decentralized welfare optimization with communication
Subjects:	Computer Science and Game Theory (cs.GT); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2609.17601 [cs.GT]
	(or arXiv:2609.17601v2 [cs.GT] for this version)
	https://doi.org/10.48550/arXiv.2609.17601 arXiv-issued DOI via DataCite

Submission history

From: Seref Taha Kiremitci [view email]
[v1] Sun, 13 Sep 2026 09:39:19 UTC (2,210 KB)
[v2] Tue, 20 Oct 2026 09:40:30 UTC (2,211 KB)