Ali̇ Devran Kara
Computer Science · University of Michigan
Publications
48
Citations
154
Est. group size
~1
Recurring co-author estimate
Active years
33
Publishing since 1993
Typically publishes in teams of ~2 · 100% small-team papers (≤3 authors) · across 8 venues
- Wasserstein Regularity of Nonlinear Filters as Belief-MDPs, and Implications on Ergodicity, Optimality and Learning for POMDPs
2025
- Sensitivity of Filter Kernels and Robustness Bounds to Transition and Measurement Kernel Perturbations in Partially Observable Stochastic Control
arXiv (Cornell University) · 2025
- Learning POMDPs with Linear Function Approximation and Finite Memory
arXiv (Cornell University) · 2025
- Quantizer Design for Finite Model Approximations, Model Learning, and Quantized Q-Learning for MDPs with Unbounded Spaces
arXiv (Cornell University) · 2025
- Average Cost Optimality of Partially Observed MDPs: Contraction of Nonlinear Filters and Existence of Optimal Solutions and Approximations
SIAM Journal on Control and Optimization · 2024
- Average Cost Optimality of Partially Observed MDPs: Contraction of Non-Linear Filters and Existence of Optimal Solutions and Approximations
2024
- Refined Bounds on Near Optimality Finite Window Policies in POMDPs and Their Reinforcement Learning
arXiv (Cornell University) · 2024
- Partially Observed Optimal Stochastic Control: Regularity, Optimality, Approximations, and Learning
arXiv (Cornell University) · 2024
- Partially Observed Optimal Stochastic Control: Regularity, Optimality, Approximations, and Learning
2024
- Q-Learning for Stochastic Control under General Information Structures and Non-Markovian Environments
arXiv (Cornell University) · 2023
- Average Cost Optimality of Partially Observed MDPS: Contraction of Non-linear Filters, Optimal Solutions and Approximations
arXiv (Cornell University) · 2023
- Approximations and Learning for Continuous State and Action MDPs under Average Cost Criteria
arXiv (Cornell University) · 2023
- Convergence of Finite Memory Q Learning for POMDPs and Near Optimality of Learned Policies Under Filter Stability
Mathematics of Operations Research · 2022
- Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control
Automatica · 2022
- Robustness to Approximations and Model Learning in MDPs and POMDPs
Emergence, complexity and computation · 2021
- arXiv (Cornell University)×20
- SIAM Journal on Control and Optimization×4
- Mathematics of Operations Research×1
- Automatica×1
- SIAM Journal on Mathematics of Data Science×1
- Nan Jiang
Computer Science · Purdue University West Lafayette
- Qinbo Bai
Computer Science · Purdue University West Lafayette
- Andrew Perrault
Computer Science · The Ohio State University
- Alejandro Murillo-González
Computer Science · Indiana University
- Abhishek Gupta
Computer Science · The Ohio State University
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 25, 2026.
Claim or correct this profile