From the 1 of 14 linked papers with an AI index.
14 papers
Monotone Inclusion Approach to Weakly Monotone Discrete-Time Finite-Horizon Mean-Field Games
Uğur Aydın, Tamer Başar, Naci Saldi
We revisit the problem of computing mean-field equilibria (MFEs) in discrete-time, monotone, finite-horizon mean-field games (MFGs). We show that, when the transition kernel is ind…
Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness
KaÄan Akman, Naci Saldi, Serdar Yüksel
The paper derives finite‑sample generalization bounds for Transformer models by formulating their training as a finite‑horizon Markovian control problem, using quantized approximat…
Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games with Average Reward
Åevket Kaan Alkır, Naci Saldı, Berkay Anahtarcı +1
We study inverse reinforcement learning for discrete-time, infinite-horizon mean-field games (MFGs) under an average-reward criterion. Expert demonstrations are assumed to arise fr…
Optimality of Symmetric Independent Policies under Decentralized Mean-Field Information Sharing for Stochastic Teams and Equivalence with McKean-Vlasov Control of a Representative Agent
Sina Sanjari, Naci Saldi, Serdar Yüksel
We study a class of stochastic exchangeable teams with a finite number of decision makers (DMs) as well as their mean-field limits with infinitely many DMs. In the finite populatio…
Approximation of Discrete-Time Infinite-Horizon Mean-Field Equilibria via Finite-Horizon Mean-Field Equilibria
UÄur Aydın, Tamer BaÅar, Naci Saldi
We address in this paper a fundamental question that arises in mean-field games (MFGs), namely whether mean-field equilibria (MFE) for discrete-time finite-horizon MFGs can be used…
Mean-Field Systems with Heterogeneous Subteams: Optimality of Cluster-Symmetric Independent Policies and Equivalence with Decentralized McKean-Vlasov Control of Cluster-Representative Agents
Connor S. Braun, Sina Sanjari, Naci Saldi +2
Across science and engineering, mean-field methods have been a powerful and versatile approach for the analysis of systems of many interacting elements. However, common arguments u…