Publications
Submitted Papers
O. Biçer, A. D. Kara, and S. Yüksel,
Quantizer Design for Finite Model Approximations, Model Learning, and Quantized Q-Learning for MDPs with Unbounded Spaces
Y. E. Demirci, A. D. Kara, and S. Yüksel,
Sensitivity of Filter Kernels and Robustness Bounds to Transition and Measurement Kernel Perturbations in Partially Observable Stochastic Control
A. D. Kara
Learning POMDPs with Linear Function Approximation and Finite Memory
Y. E. Demirci, A. D. Kara, and S. Yüksel,
Refined Bounds on Near Optimality Finite Window Policies in POMDPs and Their Reinforcement Learning
A. D. Kara and S. Yüksel,
Q-Learning for Continuous State and Action MDPs under Average Cost Criteria
Journal Publications
E. Bayraktar and A. D. Kara,
Learning with Linear Function Approximations in Mean-Field Control
Journal of Machine Learning Research, vol. 26, no. 192, pp. 1-53, 2025
E. Bayraktar, N. Bauerle, and A. D. Kara,
Finite Approximations for Mean Field Type Multi Agent Control and Their Near Optimality
Applied Mathematics and Optimization, vol. 92(7), 2025
A. D. Kara, E. Bayraktar, S. Yüksel,
Special Issue in Honor of Peter Caines's 80th Birthday, Editors: Minyi Huang and Ji-Feng Zhang, 2025 (pdf)
Approximation Schemes for POMDPs and Their Near Optimality
E. Bayraktar and A. D. Kara,
Infinite Horizon Average Cost Optimality for Mean-Field Control,
SIAM Journal on Control and Optimization, vol. 62(5), pp. 2776-2806, 2024
Y. E. Demirci, A. D. Kara, and S. Yüksel,
Average Cost Optimality of Partially Observed MDPs: Contraction of Non-linear Filters and Existence of Optimal Solutions,
SIAM Journal on Control and Optimization, vol. 62(6), pp. 2859-2883,2024
A. D. Kara and S. Yüksel,
Transactions on Machine Learning Research, 2024, (Featured Certification),
A. D. Kara and S. Yüksel,
Convergence of Finite Memory Q-Learning for POMDPs and Near Optimality of Learned Policies under Filter Stability,
Mathematics of Operations Research, vol. 48, no. 4, pp. 2066-2093, 2023.
A. D. Kara and S. Yüksel,
Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes,
Journal of Machine Learning Research, vol. 23, no. 11, pp. 1-46, 2022.
A. D. Kara, N. Saldi and S. Yüksel,
Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity,
Journal of Machine Learning Research, vol. 24, no. 199, pp. 1-34, 2023.
E. Bayraktar and A. D. Kara, Approximate Q-Learning for Controlled Diffusion Processes and its Near Optimality,
SIAM Journal on Mathematics of Data Science, vol. 5, no. 3, pp. 615-638, 2023.
A. D. Kara, M. Raginsky and S. Yüksel,
Robustness to Incorrect Models and Adaptive Learning in Average-Cost Optimal Stochastic Control,
Automatica, vol. 139(3):110179, (2022) (Editor's Choice)
A. D. Kara and S. Yüksel,
Robustness to Incorrect System Models in Stochastic Control,
SIAM Journal on Control and Optimization, vol. 58(2), pp. 1144–1182, 2020
A. D. Kara, N. Saldi and S. Yüksel,
Weak Feller Property of Non-linear Filters,
Systems and Control Letters, vol. 134, pp. 104512 Dec. 2019
A. D. Kara and S. Yüksel,
Robustness to Incorrect Priors in Partially Observed Stochastic Control,
SIAM Journal on Control and Optimization, v. 57(3), pp. 1929–1964, 2019
Book Chapters
A. D. Kara and S. Yüksel Robustness to Approximations and Model Learning in MDPs and POMDPs in Modern Trends in Controlled Stochastic Processes: Theory and Applications, Volume II. A. B. Piunovskiy and Y. Zhang, editors, Luniver Press, Frome, UK 2021 (pdf).
Conference Publications
A. D. Kara, E. Bayraktar and S. Yüksel. Near Optimality of Finite Memory Policies for POMPDs with Continuous Spaces. IEEE Conf. Decision Control, Dec. 2022
A. D. Kara and S. Yüksel. Convergence and Near Optimality of Q-Learning with Finite Memory for Partially Observed Models. IEEE Conf. Decision Control, Dec. 2021
A. D. Kara, N. Saldi and S. Yüksel. On Weak Feller Continuity Properties of Non-Linear Filters. IEEE Conf. Decision Control, Dec. 2019.
A. D. Kara, M. Raginsky and S. Yüksel. Robustness to Incorrect Models in Average-Cost Optimal Stochastic Control. IEEE Conf. Decision Control, Dec. 2019.
A. D. Kara and S. Yüksel. Robustness to Incorrect Priors in Infinite Horizon Stochastic Control. IEEE Conf. Decision Control, Dec. 2018.
A. D. Kara and S. Yüksel. Robustness to Incorrect System Models in Stochastic Control and Application to Data-Driven Learning. IEEE Conf. Decision Control, Dec. 2018, (Outstanding Student Paper Award).