Browsing Faculty of Engineering by Author "Saldı, Naci"
Now showing items 120 of 27

Approximate markovnash equilibria for discretetime risksensitive meanfield games
Saldı, Naci; Basar, T.; Raginsky, M. (Informs, 202011)In this paper, we study a class of discretetime meanfield games under the infinitehorizon risksensitive optimality criterion. Risk sensitivity is introduced for each agent (player) via an exponential utility function. ... 
Approximate nash equilibria in partially observed stochastic games with meanfield interactions
Saldı, Naci; Başar, T.; Raginsky, M. (Informs, 201908)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 finitestate approximation of a discretetime 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 finitemodel approximation of discretetime 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, 202001)We consider finite model approximations of discretetime 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 ... 
Discretetime averagecost meanfield 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 infinitepopulation ... 
Finite approximations in discretetime 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 discretetime 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. ... 
Finiteaction approximation of Markov decision processes
Saldı, Naci; Linder, T.; Yüksel, S. (Birkhäuser Basel, 2018)In this chapter, we study the finiteaction approximation of optimal control policies for discretetime Markov decision processes (MDPs) with Borel state and action spaces, under discounted and average cost criteria. One ... 
Finitestate approximation of Markov decision processes
Saldı, Naci; Linder, T.; Yüksel, S. (Springer, 2018)In this chapter we study the finitestate approximation problem for computing near optimal policies for discretetime MDPs with Borel state and action spaces, under discounted and average costs criteria. Even though existence ... 
Finitestate approximations to discounted and average cost constrained Markov decision processes
Saldı, Naci (IEEE, 201907)In this paper, we consider the finitestate approximation of a discretetime 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, 20201214)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 discretetime meanfield games
Saldı, Naci (Springer, 202111)In this paper, we establish a large deviations principle (LDP) for interacting particle systems that arise from state and action dynamics of discretetime meanfield games under the equilibrium policy of the infinitepopulation ... 
Learning in discretetime averagecost meanfield games
Anahtarcı, Berkay; Karıksız, Can Deha; Saldı, Naci (IEEE, 2021)In this paper, we consider learning of discretetime meanfield games under an average cost criterion. We propose a Qiteration algorithm via Banach Fixed Point Theorem to compute the meanfield equilibrium when the model ... 
MarkovNash equilibria in meanfield games with discounted cost
Saldı, Naci; Başar, T.; Raginsky, M. (Society for Industrial and Applied Mathematics Publications, 2018)In this paper, we consider discretetime dynamic games of the meanfield type with a finite number $N$ of agents subject to an infinitehorizon discountedcost optimality criterion. The state space of each agent is a Polish ... 
Mean field multilayer stackelberg differential games in multiagent systems
Oner, A.; Gunel, G. O.; Saldı, Naci (Ministry Communications & High Technologies Republic Azerbaijan, 2018)In this paper, we study linearquadratic hierarchical mean field Stackelberg differential games with decentralized adapted openloop information structure. In this game model, there are three levels of decision making, ... 
On weak feller continuity properties of nonlinear 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 controlfree setups this leads to the existence of invariant probability measures for compact spaces and applicability ... 
Partiallyobserved discretetime risksensitive meanfield games
Saldı, Naci; Başar, T.; Raginsky, M. (IEEE, 2019)We consider in this paper a general class of discretetime partiallyobserved meanfield games with Polish state, action, and measurement spaces and with risksensitive (exponential) cost functions which capture the ...
Share this page