Browsing Faculty of Engineering by Author "Saldı, Naci"
Now showing items 1-20 of 27
-
Approximate markov-nash equilibria for discrete-time risk-sensitive mean-field games
Saldı, Naci; Basar, T.; Raginsky, M. (Informs, 2020-11)In this paper, we study a class of discrete-time mean-field games under the infinite-horizon risk-sensitive optimality criterion. Risk sensitivity is introduced for each agent (player) via an exponential utility function. ... -
Approximate nash equilibria in partially observed stochastic games with mean-field interactions
Saldı, Naci; Başar, T.; Raginsky, M. (Informs, 2019-08)Establishing the existence of Nash equilibria for partially observed stochastic dynamic games is known to be quite challenging, with the difficulties stemming from the noisy nature of the measurements available to individual ... -
Approximations for constrained Markov decision problems
Saldı, Naci; Linder, T.; Yüksel, S. (Springer, 2018)This chapter studies the finite-state approximation of a discrete-time constrained Markov decision process with compact state space, under the discounted and average cost criteria. Using the linear programming formulation ... -
Approximations for partially observed Markov decision processes
Saldı, Naci; Linder, T.; Yüksel, S. (Birkhäuser Basel, 2018)This chapter studies the finite-model approximation of discrete-time partially observed Markov decision process. We will find that by performing the standard reduction method, where one transforms a partially observed model ... -
Asymptotic optimality of finite model approximations for partially observed markov decision processes with discounted cost
Saldı, Naci; Yuksel, S.; Linder, T. (IEEE, 2020-01)We consider finite model approximations of discrete-time partially observed Markov decision processes (POMDPs) under the discounted cost criterion. After converting the original partially observed stochastic control problem ... -
Asymptotic optimality of finite models for witsenhausen’s counterexample and beyond
Saldı, Naci; Linder, T.; Yüksel, S. (Birkhäuser Basel, 2018)In this chapter, we study the approximation of Witsenhausen’s counterexample and the Gaussian relay channel problem by using the results of the previous chapter. In particular, our goal is to establish that finite models ... -
Discrete-time average-cost mean-field games on Polish spaces
Saldı, Naci (TÜBİTAK, 2020)In stochastic dynamic games, when the number of players is sufficiently large and the interactions between agents depend on empirical state distribution, one way to approximate the original game is to introduce infinite-population ... -
Finite approximations in discrete-time stochastic control : quantized models and asymptotic optimality
Saldı, Naci; Linder, T.; Yüksel, S. (Birkhäuser Basel, 2018)In a unified form, this monograph presents fundamental results on the approximation of centralized and decentralized stochastic control problems, with uncountable state, measurement, and action spaces. It demonstrates how ... -
Finite approximations in discrete-time stochastic control quantized models and asymptotic optimality introduction and summary
Saldı, Naci; Linder, T.; Yüksel, S. (Birkhäuser Basel, 2018)Control and optimization of dynamical systems in the presence of stochastic uncertainty is a mature field with a large range of applications. A comprehensive treatment of such problems can be found in excellent books and ... -
Finite model approximations in decentralized stochastic control
Saldı, Naci; Linder, T.; Yüksel, S. (Birkhäuser Basel, 2018)In this chapter, we study the approximation of static and dynamic team problems using finite models which are obtained through the uniform discretization, on a finite grid, of the observation and action spaces of agents. ... -
Finite-action approximation of Markov decision processes
Saldı, Naci; Linder, T.; Yüksel, S. (Birkhäuser Basel, 2018)In this chapter, we study the finite-action approximation of optimal control policies for discrete-time Markov decision processes (MDPs) with Borel state and action spaces, under discounted and average cost criteria. One ... -
Finite-state approximation of Markov decision processes
Saldı, Naci; Linder, T.; Yüksel, S. (Springer, 2018)In this chapter we study the finite-state approximation problem for computing near optimal policies for discrete-time MDPs with Borel state and action spaces, under discounted and average costs criteria. Even though existence ... -
Finite-state approximations to discounted and average cost constrained Markov decision processes
Saldı, Naci (IEEE, 2019-07)In this paper, we consider the finite-state approximation of a discrete-time constrained Markov decision process (MDP) under the discounted and average cost criteria. Using the linear programming formulation of the constrained ... -
Independently randomized symmetric policies are optimal for exchangeable stochastic teams with infinitely many decision makers
Sanjari, S.; Saldı, Naci; Yüksel, S. (IEEE, 2020-12-14)We study stochastic team (known also as decentralized stochastic control or identical interest stochastic game) problems with large or countably infinite number of decision makers, and characterize existence and structural ... -
Large deviations principle for discrete-time mean-field games
Saldı, Naci (Springer, 2021-11)In this paper, we establish a large deviations principle (LDP) for interacting particle systems that arise from state and action dynamics of discrete-time mean-field games under the equilibrium policy of the infinite-population ... -
Learning in discrete-time average-cost mean-field games
Anahtarcı, Berkay; Karıksız, Can Deha; Saldı, Naci (IEEE, 2021)In this paper, we consider learning of discrete-time mean-field games under an average cost criterion. We propose a Q-iteration algorithm via Banach Fixed Point Theorem to compute the mean-field equilibrium when the model ... -
Markov-Nash equilibria in mean-field games with discounted cost
Saldı, Naci; Başar, T.; Raginsky, M. (Society for Industrial and Applied Mathematics Publications, 2018)In this paper, we consider discrete-time dynamic games of the mean-field type with a finite number $N$ of agents subject to an infinite-horizon discounted-cost optimality criterion. The state space of each agent is a Polish ... -
Mean field multilayer stackelberg differential games in multi-agent systems
Oner, A.; Gunel, G. O.; Saldı, Naci (Ministry Communications & High Technologies Republic Azerbaijan, 2018)In this paper, we study linear-quadratic hierarchical mean field Stackelberg differential games with decentralized adapted open-loop information structure. In this game model, there are three levels of decision making, ... -
On weak feller continuity properties of non-linear filters
Kara, A. D.; Saldı, Naci; Yuksel, S. (IEEE, 2019)Weak Feller property of controlled and control free Markov chains leads to many desirable properties. In control-free setups this leads to the existence of invariant probability measures for compact spaces and applicability ... -
Partially-observed discrete-time risk-sensitive mean-field games
Saldı, Naci; Başar, T.; Raginsky, M. (IEEE, 2019)We consider in this paper a general class of discrete-time partially-observed mean-field games with Polish state, action, and measurement spaces and with risk-sensitive (exponential) cost functions which capture the ...
Share this page