no code implementations • 13 Mar 2024 • Yuksel Arslantas, Ege Yuceel, Muhammed O. Sayin
In this paper, we explore the susceptibility of the Q-learning algorithm (a classical and widely used reinforcement learning method) to strategic manipulation of sophisticated opponents in games.
no code implementations • 20 Feb 2023 • Muhammed O. Sayin, Onur Unlu
We present two logit-Q learning dynamics combining the classical and independent log-linear learning updates with an on-policy value iteration update for efficient learning in stochastic games.
no code implementations • 23 Nov 2021 • Asuman Ozdaglar, Muhammed O. Sayin, Kaiqing Zhang
We focus on the development of simple and independent learning dynamics for stochastic games: each agent is myopic and chooses best-response type actions to other agents' strategy without any coordination with her opponent.
no code implementations • NeurIPS 2021 • Muhammed O. Sayin, Kaiqing Zhang, David S. Leslie, Tamer Basar, Asuman Ozdaglar
The key challenge in this decentralized setting is the non-stationarity of the environment from an agent's perspective, since both her own payoffs and the system evolution depend on the actions of other agents, and each agent adapts her policies simultaneously and independently.
no code implementations • 8 Oct 2020 • Muhammed O. Sayin, Francesca Parise, Asuman Ozdaglar
We present a novel variant of fictitious play dynamics combining classical fictitious play with Q-learning for stochastic games and analyze its convergence properties in two-player zero-sum stochastic games.
no code implementations • 22 Jul 2019 • Muhammed O. Sayin, Tamer Basar
We also quantify the approximation error for a quantized version of a continuous distribution and show that a semi-definite program relaxation of the equivalent problem could be a benchmark lower bound for the sender's cost for large state spaces.
Computer Science and Game Theory Optimization and Control
no code implementations • 30 Jan 2019 • Muhammed O. Sayin, Chung-Wei Lin, Eunsuk Kang, Shinichi Shiraishi, Tamer Basar
Recently, vision-based road sign classification algorithms have been shown to be vulnerable against (even) small scale adversarial interventions that are imperceptible for humans.
no code implementations • 22 Feb 2018 • Muhammed O. Sayin, Chung-Wei Lin, Shinichi Shiraishi, Tamer Başar
We propose a reliable intersection control mechanism for strategic autonomous and connected vehicles (agents) in non-cooperative environments.
no code implementations • 3 Oct 2016 • Muhammed O. Sayin, Suleyman S. Kozat, Tamer Başar
Finally, in the numerical examples, we demonstrate the superior performance of the introduced algorithms in the finite-horizon MSE sense due to optimal estimation.
no code implementations • 23 Jan 2014 • N. Denizcan Vanli, Muhammed O. Sayin, Suleyman S. Kozat
We study nonlinear regression of real valued data in an individual sequence manner, where we provide results that are guaranteed to hold without any statistical assumptions.
no code implementations • 26 Nov 2013 • Muhammed O. Sayin, N. Denizcan Vanli, Suleyman S. Kozat
We introduce important members of this family of algorithms such as the least mean logarithmic square (LMLS) and least logarithmic absolute difference (LLAD) algorithms that improve the convergence performance of the conventional algorithms.