no code implementations • 29 May 2024 • Naci Saldi
In this paper, we address the problem of finding the best ergodic or Birkhoff averages in the ergodic theorem to ensure rapid convergence to a desired value, using graph filters.
no code implementations • 12 Jan 2024 • Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
Subsequently, we formulate the maximum casual entropy IRL problem for MFGs - a non-convex optimization problem with respect to policies.
no code implementations • 16 Oct 2023 • Uğur Aydın, Naci Saldi
In this paper, we investigate the robustness of stationary mean-field equilibria in the presence of model uncertainties, specifically focusing on infinite-horizon discounted cost functions.
no code implementations • 14 Sep 2023 • Naci Saldi
In this paper, we demonstrate the existence of team-optimal strategies for static teams under observation-sharing information structures.
no code implementations • 15 Jan 2023 • Naci Saldi
In this paper, we introduce discrete-time linear mean-field games subject to an infinite-horizon discounted-cost optimality criterion.
no code implementations • 12 Nov 2021 • Ali Devran Kara, Naci Saldi, Serdar Yüksel
Our approach builds on (i) viewing quantization as a measurement kernel and thus a quantized MDP as a partially observed Markov decision process (POMDP), (ii) utilizing near optimality and convergence results of Q-learning for POMDPs, and (iii) finally, near-optimality of finite state model approximations for MDPs with weakly continuous kernels which we show to correspond to the fixed point of the constructed POMDP.
no code implementations • 15 Feb 2021 • Naci Saldi
In this paper, we establish a large deviations principle (LDP) for interacting particle systems that arise from state and action dynamics of discrete-time mean-field games under the equilibrium policy of the infinite-population limit.
no code implementations • 24 Mar 2020 • Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function.
no code implementations • 24 Mar 2020 • Naci Saldi, Tamer Basar, Maxim Raginsky
In this paper, we consider discrete-time partially observed mean-field games with the risk-sensitive optimality criterion.
no code implementations • 31 Dec 2019 • Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
We consider learning approximate Nash equilibria for discrete-time mean-field games with nonlinear stochastic state dynamics subject to both average and discounted costs.