no code implementations • 26 Mar 2024 • Bora Yongacoglu, Gürdal Arslan, Lacra Pavel, Serdar Yüksel
In multi-agent reinforcement learning (MARL), agents repeatedly interact across time and revise their strategies as new data arrives, producing a sequence of strategy profiles.
no code implementations • 7 Aug 2023 • Bora Yongacoglu, Gürdal Arslan, Serdar Yüksel
In this paper, we study an asynchronous variant of the decentralized Q-learning algorithm, a recent MARL algorithm for stochastic games.
1 code implementation • 16 Mar 2023 • Awni Altabaa, Bora Yongacoglu, Serdar Yüksel
Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL).
no code implementations • 12 Nov 2021 • Ali Devran Kara, Naci Saldi, Serdar Yüksel
Our approach builds on (i) viewing quantization as a measurement kernel and thus a quantized MDP as a partially observed Markov decision process (POMDP), (ii) utilizing near optimality and convergence results of Q-learning for POMDPs, and (iii) finally, near-optimality of finite state model approximations for MDPs with weakly continuous kernels which we show to correspond to the fixed point of the constructed POMDP.
no code implementations • 9 Oct 2021 • Bora Yongacoglu, Gürdal Arslan, Serdar Yüksel
In multi-agent reinforcement learning (MARL), independent learners are those that do not observe the actions of other agents in the system.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 11 Mar 2021 • Ari Arapostathis, Serdar Yüksel
The convex analytic method has proved to be a very versatile method for the study of infinite horizon average cost optimal stochastic control problems.
Optimization and Control 90C40, 93E20
no code implementations • 15 Dec 2020 • Ertan Kazıklı, Serkan Sarıtaş, Sinan Gezici, Tamás Linder, Serdar Yüksel
For sources with two-sided unbounded support, we prove that, for any finite number of bins, there exists a unique equilibrium.
Quantization Information Theory Information Theory
no code implementations • 12 May 2020 • Ertan Kazıklı, Sinan Gezici, Serdar Yüksel
We show that this MMSE Gaussian Information Bottleneck Problem admits a linear solution which is explicitly characterized in the paper.
Information Theory Information Theory Optimization and Control
no code implementations • 25 Jun 2015 • Gürdal Arslan, Serdar Yüksel
There are only a few learning algorithms applicable to stochastic dynamic teams and games which generalize Markov decision processes to decentralized stochastic control problems involving possibly self-interested decision makers.