{"ID":22919620,"CreatedAt":"2026-09-17T01:02:08.507062015Z","UpdatedAt":"2026-09-20T09:33:40.597222295Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.17601","arxiv_id":"2609.17601","title":"Decentralized Optimal Equilibrium Learning Over Dynamic Networks","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.","short_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 netw...","url_abs":"https://arxiv.org/abs/2609.17601","url_pdf":"https://arxiv.org/pdf/2609.17601v1","authors":"[\"Seref Taha Kiremitci\",\"Muhammed O. Sayin\"]","published":"2026-09-13T09:39:19Z","proceeding":"cs.GT","tasks":"[\"cs.GT\",\"cs.AI\",\"cs.LG\"]","methods":"[\"LoRA\"]","has_code":false}