Share This Author
A New Approach to Linear Filtering and Prediction Problems
- T. Başar
The clssical filleting and prediclion problem is re-examined using the Bode-Shannon representation of random processes and the ?stat-tran-sition? method of analysis of dynamic systems. New result…
Dynamic Noncooperative Game Theory
H∞-0ptimal Control and Related Minimax Design Problems: A Dynamic Game Approach
The authors believe that the H-infinity-optimal control theory is now at a stage where it can easily be incorporated into a second-level graduate course in a control curriculum, that would follow a basic course in linear control theory covering LQ and LQG designs.
Coalitional game theory for communication networks
- W. Saad, Zhu Han, M. Debbah, A. Hjørungnes, T. Başar
- Computer ScienceIEEE Signal Processing Magazine
- 25 May 2009
This article fills a void in existing communications literature, by providing a novel tutorial on applying coalitional game theory in communication networks through comprehensive theory and technical details as well as through practical examples drawn from both game theory and communication application.
Analysis of Recursive Stochastic Algorithms
- T. Başar
- Computer Science
Dynamic Noncooperative Game Theory, 2nd Edition
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
- K. Zhang, Zhuoran Yang, Han Liu, Tong Zhang, T. Başar
- Computer Science, MathematicsICML
- 23 February 2018
This work appears to be the first study of fully decentralized MARL algorithms for networked agents with function approximation, with provable convergence guarantees, and can be implemented in an online fashion.
H1-Optimal Control and Related Minimax Design Problems
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
This chapter reviews the theoretical results of MARL algorithms mainly within two representative frameworks, Markov/stochastic games and extensive-form games, in accordance with the types of tasks they address, i.e., fully cooperative, fully competitive, and a mix of the two.