67 citations · 227 across the 41 of their papers we have counts for
47 papers
Approximations and Learning for Decentralized Stochastic Control and Near Optimal Finite Window Policies
Omar Mrani-Zentar, Serdar Yuksel
Decentralized stochastic control problems are difficult to study due to information structure dependent subtleties, which prevent many classical methods in stochastic control from…
Mean-Field Systems with Heterogeneous Subteams: Optimality of Cluster-Symmetric Independent Policies and Equivalence with Decentralized McKean-Vlasov Control of Cluster-Representative Agents
Connor S. Braun, Sina Sanjari, Naci Saldi +2
Across science and engineering, mean-field methods have been a powerful and versatile approach for the analysis of systems of many interacting elements. However, common arguments u…
Reinforcement Learning for Discounted and Ergodic Control of Diffusion Processes
Erhan Bayraktar, Ali D. Kara, Somnath Pradhan +1
This paper develops a quantized Q-learning algorithm for the optimal control of controlled diffusion processes on under both discounted and ergodic (average) cost cr…
Near Optimality of Discrete-Time Approximations for Controlled McKean-Vlasov and Large Interacting Particle Diffusions
Somnath Pradhan, Serdar Yuksel
We study stochastic optimal control problems for (possibly degenerate) McKean-Vlasov controlled diffusions and obtain discrete-time as well as finite interacting particle approxima…
Sensitivity of Filter Kernels and Robustness Bounds to Transition and Measurement Kernel Perturbations in Partially Observable Stochastic Control
Yunus Emre Demirci, Ali Devran Kara, Serdar Yüksel
Studying the stability of partially observed Markov decision processes (POMDPs) with respect to perturbations in either transition or observation kernels is a significant problem.…
Discrete-Time Approximations of Controlled Diffusions with Infinite Horizon Discounted and Average Cost
Somnath Pradhan, Serdar Yuksel
We present discrete-time approximation of optimal control policies for infinite horizon discounted/ergodic control problems for controlled diffusions in $\Rd$\,. In particular, our…
General-Sum Markov Games with Borel Spaces: Existence of Approximate Nash Equilibria via Finite Model Approximations under Setwise or Weak Continuity
Naci Saldi, Gurdal Arslan, Serdar Yuksel
Establishing the existence of exact or near Markov or stationary perfect Nash equilibria in nonzero-sum Markov games over Borel spaces is a challenging problem with limited positiv…
Near Optimal Approximations and Finite Memory Policies for POMPDs with Continuous Spaces
Ali Devran Kara, Erhan Bayraktar, Serdar Yuksel
We study an approximation method for partially observed Markov decision processes (POMDPs) with continuous spaces. Belief MDP reduction, which has been the standard approach to stu…
Refined Bounds on Near Optimality Finite Window Policies in POMDPs and Their Reinforcement Learning
Yunus Emre Demirci, Ali Devran Kara, Serdar Yüksel
Finding optimal policies for Partially Observable Markov Decision Processes (POMDPs) is challenging due to their uncountable state spaces when transformed into fully observable Mar…
Centralized Reduction of Decentralized Stochastic Control Models and their weak-Feller Regularity
Omar Mrani-Zentar, Serdar Yüksel
Decentralized stochastic control problems involving general state/measurement/action spaces are intrinsically difficult to study because of the inapplicability of standard tools fr…
Near Optimality of Lipschitz and Smooth Policies in Controlled Diffusions
Somnath Pradhan, Serdar Yuksel
For optimal control of diffusions under several criteria, due to computational or analytical reasons, many studies have a apriori assumed control policies to be Lipschitz or smooth…
Decentralized Exchangeable Stochastic Dynamic Teams in Continuous-time, their Mean-Field Limits and Optimality of Symmetric Policies
Sina Sanjari, Naci Saldi, Serdar Yüksel
We study a class of stochastic exchangeable teams comprising a finite number of decision makers (DMs) as well as their mean-field limits involving infinite numbers of DMs. In the f…
Subjective Equilibria under Beliefs of Exogenous Uncertainty: Linear Quadratic Case
Gürdal Arslan, Serdar Yüksel
We consider a stochastic dynamic game where players have their own linear state dynamics and quadratic cost functions. Players are coupled through some environment variables, gener…
Satisficing Paths to Equilibrium, Generalized Weakly Acyclic Games, and Learning
Bora Yongacoglu, Gwendolen Hickey, Gürdal Arslan +2
Weakly acyclic games generalize potential games and have shown to be fundamental in the study of multi-agent learning as they allow for convergence to an equilibrium via best-respo…
Paths to Equilibrium in Games
Bora Yongacoglu, Gürdal Arslan, Lacra Pavel +1
In multi-agent reinforcement learning (MARL) and game theory, agents repeatedly interact and revise their strategies as new data arrives, producing a sequence of strategy profiles.…
Average Cost Optimality of Partially Observed MDPS: Contraction of Non-linear Filters, Optimal Solutions and Approximations
Yunus Emre Demirci, Ali Devran Kara, Serdar Yüksel
The average cost optimality is known to be a challenging problem for partially observable stochastic control, with few results available beyond the finite state, action, and measur…
Controlled Diffusions under Full, Partial and Decentralized Information: Existence of Optimal Policies and Discrete-Time Approximations
Somnath Pradhan, Serdar Yüksel
We present existence and discrete-time approximation results on optimal control policies for continuous-time stochastic control problems under a variety of information structures.…
Robustness of Optimal Controlled Diffusions with Near-Brownian Noise via Rough Paths Theory
Somnath Pradhan, Zachary Selk, Serdar Yüksel
In this article we show a robustness theorem for controlled stochastic differential equations driven by approximations of Brownian motion. Often, Brownian motion is used as an idea…
Sliding Window Codes: Near-Optimality and Q-Learning for Zero-Delay Coding
Liam Cregg, Fady Alajaji, Serdar Yuksel
We study the problem of zero-delay coding for the transmission of a Markov source over a noisy channel with feedback and present a reinforcement learning solution which is guarante…
Approximations and Learning for Continuous State and Action MDPs under Average Cost Criteria
Ali Devran Kara, Serdar Yuksel
In this paper, for Markov Decision Processes (MDPs) with standard Borel spaces, (i) we first provide a discretization based approximation method for MDPs with continuous spaces und…
Unsynchronized Decentralized Q-Learning: Two Timescale Analysis By Persistence
Bora Yongacoglu, Gürdal Arslan, Serdar Yüksel
Non-stationarity is a fundamental challenge in multi-agent reinforcement learning (MARL), where agents update their behaviour as they learn. Many theoretical advances in MARL avoid…
Unique Ergodicity of Non-Linear Filters via Reachability and Uniform Weak Continuity
Yunus Emre Demirci, Serdar Yüksel
We present a reachability based approach to establish unique ergodicity of non-linear filter processes where state space of a hidden Markov model is a compact Polish metric space a…
Nash Equilibria for Exchangeable Team against Team Games, their Mean Field Limit, and Role of Common Randomness
Sina Sanjari, Naci Saldi, Serdar Yüksel
We study stochastic mean-field games among finite number of teams with large finite as well as infinite number of decision makers. For this class of games within static and dynamic…
Non-Sequential Decentralized Stochastic Control Revisited: Causality and Static Reducibility
Omar Mrani-Zentar, Ryan Simpson, Serdar Yüksel
In decentralized stochastic control (or stochastic team theory) and game theory, if there is a pre-defined order in a system in which agents act, the system is called \textit{seque…