Follow
Ali Devran Kara
Ali Devran Kara
Verified email at umich.edu - Homepage
Title
Cited by
Cited by
Year
Near optimality of finite memory feedback policies in partially observed markov decision processes
A Kara, S Yuksel
Journal of Machine Learning Research 23 (11), 1-46, 2022
292022
Convergence of finite memory Q learning for POMDPs and near optimality of learned policies under filter stability
AD Kara, S Yüksel
Mathematics of Operations Research 48 (4), 2066-2093, 2023
282023
Robustness to incorrect system models in stochastic control
AD Kara, S Yuksel
SIAM Journal on Control and Optimization 58 (2), 1144-1182, 2020
282020
Weak Feller property of non-linear filters
AD Kara, N Saldi, S Yüksel
Systems & Control Letters 134, 104512, 2019
282019
Robustness to incorrect priors in partially observed stochastic control
AD Kara, S Yüksel
SIAM Journal on Control and Optimization 57 (3), 1929-1964, 2019
222019
Q-learning for MDPs with general spaces: Convergence and near optimality via quantization under weak continuity
A Kara, N Saldi, S Yüksel
Journal of Machine Learning Research 24 (199), 1-34, 2023
142023
Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control
AD Kara, M Raginsky, S Yüksel
Automatica 139, 110179, 2022
92022
Robustness to incorrect system models in stochastic control and application to data-driven learning
AD Kara, S Yüksel
2018 IEEE Conference on Decision and Control (CDC), 2753-2758, 2018
72018
Approximate q learning for controlled diffusion processes and its near optimality
E Bayraktar, AD Kara
SIAM Journal on Mathematics of Data Science 5 (3), 615-638, 2023
32023
Finite Approximations and Q learning for Mean Field Type Multi Agent Control
E Bayraktar, N Bäuerle, AD Kara
arXiv preprint arXiv:2211.09633, 2022
32022
Robustness to approximations and model learning in MDPs and POMDPs
AD Kara, S Yüksel
Modern Trends in Controlled Stochastic Processes: Theory and Applications, V …, 2021
32021
Robustness to incorrect models in average-cost optimal stochastic control
AD Kara, M Raginsky, S Yüksel
2019 IEEE 58th Conference on Decision and Control (CDC), 7970-7975, 2019
32019
Q-learning for continuous state and action mdps under average cost criteria
AD Kara, S Yuksel
arXiv preprint arXiv:2308.07591, 2023
12023
Near Optimality of Finite Memory Policies for POMPDs with Continuous Spaces
AD Kara, E Bayraktar, S Yüksel
2022 IEEE 61st Conference on Decision and Control (CDC), 2301-2306, 2022
12022
Finite Approximations for Mean Field Type Multi-Agent Control and Their Near Optimality
E Bayraktar, N Bauerle, AD Kara
arXiv preprint arXiv:2211.09633, 2022
12022
Convergence and Near Optimality of Q-Learning with Finite Memory for Partially Observed Models
AD Kara, S Yüksel
2021 60th IEEE Conference on Decision and Control (CDC), 1603-1608, 2021
12021
Average Cost Optimality of Partially Observed MDPs: Contraction of Non-linear Filters and Existence of Optimal Solutions
YE Demirci, AD Kara, S Yüksel
arXiv preprint arXiv:2312.14111, 2023
2023
Q-Learning for Stochastic Control under General Information Structures and Non-Markovian Environments
AD Kara, S Yuksel
arXiv preprint arXiv:2311.00123, 2023
2023
Infinite Horizon Average Cost Optimality Criteria for Mean-Field Control
E Bayraktar, AD Kara
arXiv preprint arXiv:2309.11744, 2023
2023
On weak feller continuity properties of non-linear filters
AD Kara, N Saldi, S Yüksel
2019 IEEE 58th Conference on Decision and Control (CDC), 654-659, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–20