5 papers
Independent Reinforcement Learning in Discounted Markov Games
Asrin Efe Yorulmaz, Ugur Aydin, Tamer Basar
In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming `` for ", we show that, for every fixed discount f…
A Stackelberg Game Framework with Drainability Guardrails for Pricing and Scaling in Multi-Tenant GPU Cloud Platforms
Junji Yan, Asrin Efe Yorulmaz, Hanchen Zhou +1
Modern Graphics Processing Unit (GPU)-backed services must satisfy strict latency service-level objectives (SLOs) while controlling spare-capacity costs. In multi-tenant GPU cloud…
Meta-Learning for Repeated Bayesian Persuasion
Ata Poyraz Turna, Asrin Efe Yorulmaz, Tamer Başar
Classical Bayesian persuasion studies how a sender influences receivers through carefully designed signaling policies within a single strategic interaction. In many real-world envi…
Near Optimal Convergence to Coarse Correlated Equilibrium in General-Sum Markov Games
Asrin Efe Yorulmaz, Tamer Başar
No-regret learning dynamics play a central role in game theory, enabling decentralized convergence to equilibrium for concepts such as Coarse Correlated Equilibrium (CCE) or Correl…
A Soft Inducement Framework for Incentive-Aided Steering of No-Regret Players
Asrin Efe Yorulmaz, Raj Kiriti Velicheti, Melih Bastopcu +1
In this work, we investigate a steering problem in a mediator-augmented two-player normal-form game, where the mediator aims to guide players toward a specific action profile throu…