Q-learning in regularized mean-field games

B Anahtarci, CD Kariksiz, N Saldi - Dynamic Games and Applications, 2023 - Springer
In this paper, we introduce a regularized mean-field game and study learning of this game
under an infinite-horizon discounted reward function. Regularization is introduced by adding …

Average Cost Optimality of Partially Observed MDPs: Contraction of Nonlinear Filters and Existence of Optimal Solutions and Approximations

YE Demirci, AD Kara, S Yüksel - SIAM Journal on Control and Optimization, 2024 - SIAM
The average cost optimality is known to be a challenging problem for partially observable
stochastic control, with few results available beyond the finite state, action, and …

On Borkar and Young relaxed control topologies and continuous dependence of invariant measures on control policy

S Yüksel - SIAM Journal on Control and Optimization, 2024 - SIAM
In deterministic and stochastic control theory, relaxed or randomized control policies allow
for versatile mathematical analysis (on continuity, compactness, convexity, and …

Partially Observed Optimal Stochastic Control: Regularity, Optimality, Approximations, and Learning

AD Kara, S Yuksel - arXiv preprint arXiv:2412.06735, 2024 - arxiv.org
In this review/tutorial article, we present recent progress on optimal control of partially
observed Markov Decision Processes (POMDPs). We first present regularity and continuity …

Robustness to incorrect priors and controlled filter stability in partially observed stochastic control

C McDonald, S Yüksel - SIAM Journal on Control and Optimization, 2022 - SIAM
We study controlled filter stability and its effects on the robustness properties of optimal
control policies designed for systems with incorrect priors applied to a true system. Filter …

Robustness to incorrect system models in stochastic control

AD Kara, S Yuksel - SIAM Journal on Control and Optimization, 2020 - SIAM
In stochastic control applications, typically only an ideal model (controlled transition kernel)
is assumed and the control design is based on the given model, raising the problem of …

Robustness and Approximation of Discrete-time Mean-field Games under Discounted Cost Criterion

U Aydın, N Saldi - arXiv preprint arXiv:2310.10828, 2023 - arxiv.org
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 …

Continuity properties of value functions in information structures for zero-sum and general games and stochastic teams

I Hogeboom-Burr, S Yüksel - SIAM Journal on Control and Optimization, 2023 - SIAM
We study continuity properties of stochastic game problems with respect to various
topologies on information structures, defined as probability measures characterizing a …

Signaling-based Robust Incentive Designs with Randomized Monitoring

S Sanjari, S Bose, T Başar - IFAC-PapersOnLine, 2023 - Elsevier
Incentive design problems entail hierarchical decision-making where a leader crafts a
strategy to induce a desired response from a follower. Such dynamic games with …

Robustness to approximations and model learning in MDPs and POMDPs

AD Kara, S Yüksel - Modern Trends in Controlled Stochastic Processes …, 2021 - Springer
In stochastic control applications, typically only an ideal model (controlled transition kernel)
is assumed and the control design is based on the given model, raising the problem of …