• Publications
  • Influence
Decentralized Q-Learning for Stochastic Teams and Games
TLDR
This paper presents decentralized Q-learning algorithms for stochastic games, and studies their convergence for the weakly acyclic case which includes team problems as an important special case.
Stochastic Stabilization of Noisy Linear Systems With Fixed-Rate Limited Feedback
  • S. Yüksel
  • Mathematics, Computer Science
    IEEE Transactions on Automatic Control
  • 27 September 2010
TLDR
Stochastic stability results for simple adaptive quantizers when the system noise has unbounded support for its probability measure are presented and it is shown that, there exists a unique invariant distribution for the state and the quantizer parameters under mild conditions.
Information structures in optimal decentralized control
TLDR
A comprehensive characterization of information structures in team decision problems and their impact on the tractability of team optimization and norm-optimal control for linear plants under information constraints is provided.
Optimization and convergence of observation channels in stochastic control
  • S. Yüksel, T. Linder
  • Mathematics
    Proceedings of the American Control Conference
  • 20 September 2010
TLDR
The paper explains why a class of decentralized control problems, under the non-classical information structure, is non-convex when signaling is present and shows that the optimization is concave in observation channels.
Control Over Noisy Forward and Reverse Channels
  • S. Yüksel, T. Başar
  • Computer Science, Mathematics
    IEEE Transactions on Automatic Control
  • 1 May 2011
TLDR
It is shown that under variable-length coding and some realistic channel conditions, stability can be achieved over discrete-alphabet channels even if the entire state and control spaces are to be encoded and the number of bits that can be transmitted per unit time is strictly bounded.
Random-Time, State-Dependent Stochastic Drift for Markov Chains and Application to Stochastic Stabilization Over Erasure Channels
TLDR
It is shown that stability of the closed loop system is assured provided that the channel capacity is greater than the logarithm of the unstable eigenvalue, plus an additional correction term.
Stationary and Ergodic Properties of Stochastic NonLinear Systems Controlled over Communication Channels
  • S. Yüksel
  • Mathematics
    SIAM J. Control. Optim.
  • 12 June 2015
TLDR
A generalization of Bode's Integral Formula for a large class of non-linear systems and information channels is obtained and generalize existing results for linear systems.
A Universal Dynamic Program and Refined Existence Results for Decentralized Stochastic Control
  • S. Yüksel
  • Mathematics
    SIAM J. Control. Optim.
  • 9 March 2020
TLDR
A general (universally applicable) dynamic programming formulation is introduced, its well-posedness is established, and new existence results for optimal policies in decentralized stochastic control are obtained.
...
1
2
3
4
5
...