Naci Saldi - RankMe

81 papers B 1C 5Journal 56Unranked 19

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	An Optimal Control Approach To Transformer Training. CoRR Kagan Akman, Naci Saldi, Serdar Yüksel
2026	J	`jnl`	Linear Mean-Field Games with Discounted Cost. Math. Oper. Res. Naci Saldi
2026	J	`jnl`	Robustness and Approximation of Discrete-Time Mean-Field Games Under Discounted Cost Criterion. Math. Oper. Res. Ugur Aydin, Naci Saldi
2025	—	`conf`	Approximation of Discrete-Time Infinite-Horizon Mean-Field Equilibria via Finite-Horizon Mean-Field Equilibria. CDC Ugur Aydin, Tamer Basar, Naci Saldi
2025	—	`conf`	Inverse Reinforcement Learning for Mean-field Games with Average Reward Criterion. CDC Sevket Kaan Alkir, Naci Saldi
2025	J	`jnl`	Kernel Based Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games. CoRR Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2025	—	`conf`	Kernel Mean Embedding Topology: Weak and Strong Forms for Stochastic Kernels and Implications for Model Learning. CDC Naci Saldi, Serdar Yüksel
2025	J	`jnl`	Kernel Mean Embedding Topology: Weak and Strong Forms for Stochastic Kernels and Implications for Model Learning. CoRR Naci Saldi, Serdar Yüksel
2025	J	`jnl`	Maximum Causal Entropy IRL in Mean-Field Games and GNEP Framework for Forward RL. J. Mach. Learn. Res. Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2025	J	`jnl`	Quantum Markov Decision Processes: General Theory, Approximations, and Classes of Policies. SIAM J. Control. Optim. Naci Saldi, Sina Sanjari, Serdar Yüksel
2024	J	`jnl`	Best Ergodic Averages via Optimal Graph Filters in Reversible Markov Chains. CoRR Naci Saldi
2024	J	`jnl`	Existence of ε-Nash Equilibria in Nonzero-Sum Borel Stochastic Games and Equilibria of Quantized Models. CoRR Naci Saldi, Gürdal Arslan, Serdar Yüksel
2024	C	`conf`	Large Decentralized Continuous-Time Convex Stochastic Teams and Their Mean-Field Limits. ACC Sina Sanjari, Naci Saldi, Serdar Yüksel
2024	J	`jnl`	Maximum Causal Entropy Inverse Reinforcement Learning for Mean-Field Games. CoRR Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2024	J	`jnl`	Nash Equilibria for Exchangeable Team-Against-Team Games, Their Mean-Field Limit, and the Role of Common Randomness. SIAM J. Control. Optim. Sina Sanjari, Naci Saldi, Serdar Yüksel
2024	—	`conf`	Optimality of Decentralized Symmetric Policies for Stochastic Teams with Mean-Field Information Sharing. CDC Sina Sanjari, Naci Saldi, Serdar Yüksel
2024	J	`jnl`	Quantum Markov Decision Processes Part I: General Theory, Approximations, and Classes of Policies. CoRR Naci Saldi, Sina Sanjari, Serdar Yüksel
2024	J	`jnl`	Quantum Markov Decision Processes Part II: Optimal Solutions and Algorithms. CoRR Naci Saldi, Sina Sanjari, Serdar Yüksel
2024	—	`conf`	Quantum Markov Decision Processes. CDC Naci Saldi, Sina Sanjari, Serdar Yüksel
2023	J	`jnl`	Common Information Approach for Static Team Problems with Polish Spaces and Existence of Optimal Policies. CoRR Naci Saldi
2023	J	`jnl`	Learning Mean-Field Games with Discounted and Average Costs. J. Mach. Learn. Res. Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2023	J	`jnl`	Linear Mean-Field Games with Discounted Cost. CoRR Naci Saldi
2023	C	`conf`	Nash Equilibria for Exchangeable Team against Team Games and their Mean Field Limit. ACC Sina Sanjari, Naci Saldi, Serdar Yüksel
2023	J	`jnl`	Optimality of Independently Randomized Symmetric Policies for Exchangeable Stochastic Teams with Infinitely Many Decision Makers. Math. Oper. Res. Sina Sanjari, Naci Saldi, Serdar Yüksel
2023	J	`jnl`	Partially Observed Discrete-Time Risk-Sensitive Mean Field Games. Dyn. Games Appl. Naci Saldi, Tamer Basar, Maxim Raginsky
2023	J	`jnl`	Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity. J. Mach. Learn. Res. Ali Devran Kara, Naci Saldi, Serdar Yüksel
2023	J	`jnl`	Q-Learning in Regularized Mean-field Games. Dyn. Games Appl. Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2023	J	`jnl`	Robustness and Approximation of Discrete-time Mean-field Games under Discounted Cost Criterion. CoRR Ugur Aydin, Naci Saldi
2022	J	`jnl`	Nash Equilibria for Exchangeable Team against Team Games and their Mean Field Limit. CoRR Sina Sanjari, Naci Saldi, Serdar Yüksel
2021	J	`jnl`	Large Deviations Principle for Discrete-time Mean-field Games. CoRR Naci Saldi
2021	J	`jnl`	Large deviations principle for discrete-time mean-field games. Syst. Control. Lett. Naci Saldi
2021	—	`conf`	Learning in Discrete-time Average-cost Mean-field Games. CDC Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2021	J	`jnl`	Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity. CoRR Ali Devran Kara, Naci Saldi, Serdar Yüksel
2021	J	`jnl`	Regularized stochastic team problems. Syst. Control. Lett. Naci Saldi
2020	J	`jnl`	A Topology for Team Policies and Existence of Optimal Team Policies in Stochastic Team Theory. IEEE Trans. Autom. Control. Naci Saldi
2020	J	`jnl`	Approximate Markov-Nash Equilibria for Discrete-Time Risk-Sensitive Mean-Field Games. Math. Oper. Res. Naci Saldi, Tamer Basar, Maxim Raginsky
2020	J	`jnl`	Asymptotic Optimality of Finite Model Approximations for Partially Observed Markov Decision Processes With Discounted Cost. IEEE Trans. Autom. Control. Naci Saldi, Serdar Yüksel, Tamás Linder
2020	—	`conf`	Independently Randomized Symmetric Policies are Optimal for Exchangeable Stochastic Teams with Infinitely Many Decision Makers. CDC Sina Sanjari, Naci Saldi, Serdar Yüksel
2020	J	`jnl`	Partially Observed Discrete-Time Risk-Sensitive Mean Field Games. CoRR Naci Saldi, Tamer Basar, Maxim Raginsky
2020	J	`jnl`	Q-Learning in Regularized Mean-field Games. CoRR Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2020	J	`jnl`	Regularized Stochastic Team Problems. CoRR Naci Saldi
2020	J	`jnl`	Value iteration algorithm for mean-field games. Syst. Control. Lett. Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2019	J	`jnl`	Approximate Nash Equilibria in Partially Observed Stochastic Games with Mean-Field Interactions. Math. Oper. Res. Naci Saldi, Tamer Basar, Maxim Raginsky
2019	J	`jnl`	Discrete-time average-cost mean-field games on Polish spaces. CoRR Naci Saldi
2019	J	`jnl`	Finite-State Approximations to Discounted and Average Cost Constrained Markov Decision Processes. IEEE Trans. Autom. Control. Naci Saldi
2019	J	`jnl`	Fitted Q-Learning in Mean-field Games. CoRR Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2019	—	`conf`	On Weak Feller Continuity Properties of Non-linear Filters. CDC Ali Devran Kara, Naci Saldi, Serdar Yüksel
2019	—	`conf`	Partially-Observed Discrete-Time Risk-Sensitive Mean-Field Games. CDC Naci Saldi, Tamer Basar, Maxim Raginsky
2019	J	`jnl`	Value Iteration Algorithm for Mean-field Games. CoRR Berkay Anahtarci, Can Deha Kariksiz, Naci Saldi
2019	J	`jnl`	Weak Feller property of non-linear filters. Syst. Control. Lett. Ali Devran Kara, Naci Saldi, Serdar Yüksel
2018	—	`conf`	A Topology for Policies in Decentralized Stochastic Control and Existence of Optimal Policies. CDC Naci Saldi
2018	J	`jnl`	Discrete-time Risk-sensitive Mean-field Games. CoRR Naci Saldi, Tamer Basar, Maxim Raginsky
2018	J	`jnl`	Markov-Nash Equilibria in Mean-Field Games with Discounted Cost. SIAM J. Control. Optim. Naci Saldi, Tamer Basar, Maxim Raginsky
2017	J	`jnl`	A topology for Team Policies and Existence of Optimal Team Policies in Stochastic Team Theory. CoRR Naci Saldi
2017	J	`jnl`	Approximate Nash Equilibria in Partially Observed Stochastic Games with Mean-Field Interactions. CoRR Naci Saldi, Tamer Basar, Maxim Raginsky
2017	J	`jnl`	Convex Analysis in Decentralized Stochastic Control, Strategic Measures, and Optimal Solutions. SIAM J. Control. Optim. Serdar Yüksel, Naci Saldi
2017	J	`jnl`	Finite Model Approximations and Asymptotic Optimality of Quantized Policies in Decentralized Stochastic Control. IEEE Trans. Autom. Control. Naci Saldi, Serdar Yüksel, Tamás Linder
2017	J	`jnl`	Finite Model Approximations for Partially Observed Markov Decision Processes with Discounted Cost. CoRR Naci Saldi, Serdar Yüksel, Tamás Linder
2017	C	`conf`	Markov-Nash equilibria in mean-field games with discounted cost. ACC Naci Saldi, Tamer Basar, Maxim Raginsky
2017	J	`jnl`	On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces. Math. Oper. Res. Naci Saldi, Serdar Yüksel, Tamás Linder
2016	C	`conf`	Asymptotic optimality of finite representations and quantized policies in team problems and Witsenhausen's counterexample. ACC Naci Saldi, Serdar Yüksel, Tamás Linder
2016	—	`conf`	Convex analysis in decentralized stochastic control and strategic measures. CDC Serdar Yüksel, Naci Saldi
2016	—	`conf`	Finite model approximations and asymptotic optimality of quantized policies in decentralized stochastic control. CDC Naci Saldi, Serdar Yüksel, Tamás Linder
2016	J	`jnl`	Markov-Nash Equilibria in Mean-Field Games with Discounted Cost. CoRR Naci Saldi, Tamer Basar, Maxim Raginsky
2016	—	`conf`	Strategic measures approach to decentralized stochastic control. Allerton Serdar Yüksel, Naci Saldi
2015	J	`jnl`	Asymptotic Optimality and Rates of Convergence of Quantized Stationary Policies in Stochastic Control. IEEE Trans. Autom. Control. Naci Saldi, Tamás Linder, Serdar Yüksel
2015	J	`jnl`	Asymptotic Optimality of Finite Approximations to Markov Decision Processes with General State and Action Spaces. CoRR Naci Saldi, Serdar Yüksel, Tamás Linder
2015	J	`jnl`	Finite Model Approximations and Asymptotic Optimality of Quantized Policies in Decentralized Stochastic Control. CoRR Naci Saldi, Serdar Yüksel, Tamás Linder
2015	C	`conf`	Finite state approximations of Markov decision processes with general state and action spaces. ACC Naci Saldi, Tamás Linder, Serdar Yüksel
2015	—	`conf`	Finite-state approximation of Markov decision processes with unbounded costs and Borel spaces. CDC Naci Saldi, Serdar Yüksel, Tamás Linder
2015	—	`conf`	Finite-state approximations to constrained Markov decision processes with Borel spaces. Allerton Naci Saldi, Serdar Yüksel, Tamás Linder
2015	J	`jnl`	Output Constrained Lossy Source Coding With Limited Common Randomness. IEEE Trans. Inf. Theory Naci Saldi, Tamás Linder, Serdar Yüksel
2015	J	`jnl`	Randomized Quantization and Source Coding With Constrained Output Distribution. IEEE Trans. Inf. Theory Naci Saldi, Tamás Linder, Serdar Yüksel
2014	—	`conf`	Asymptotic optimality of quantized policies in stochastic control under weak continuity conditions. CDC Naci Saldi, Tamás Linder, Serdar Yüksel
2014	J	`jnl`	Output Constrained Lossy Source Coding with Limited Common Randomness. CoRR Naci Saldi, Tamás Linder, Serdar Yüksel
2014	—	`conf`	Randomized source coding with limited common randomness. Allerton Naci Saldi, Tamás Linder, Serdar Yüksel
2013	—	`conf`	Approximation of stationary control policies by quantized control in Markov decision processes. Allerton Naci Saldi, Tamás Linder, Serdar Yüksel
2013	J	`jnl`	Quantized Stationary Control Policies in Markov Decision Processes. CoRR Naci Saldi, Tamás Linder, Serdar Yüksel
2013	J	`jnl`	Randomized Quantization and Source Coding with Constrained Output Distribution. CoRR Naci Saldi, Tamás Linder, Serdar Yüksel
2013	B	`conf`	Randomized quantization and optimal design with a marginal constraint. ISIT Naci Saldi, Tamás Linder, Serdar Yüksel
2012	—	`conf`	Blind image restoration by employing an optimized wiener filter. SIU Ziya Gurkan Figen, Naci Saldi