Search Results for author: Muhammed O. Sayin

Found 11 papers, 0 papers with code

Strategizing against Q-learners: A Control-theoretical Approach

no code implementations13 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.

Q-Learning Quantization

Logit-Q Dynamics for Efficient Learning in Stochastic Teams

no code implementations20 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.

Q-Learning

Independent Learning in Stochastic Games

no code implementations23 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.

Autonomous Driving Reinforcement Learning (RL)

Decentralized Q-Learning in Zero-sum Markov Games

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.

Multi-agent Reinforcement Learning Q-Learning

Fictitious play in zero-sum stochastic games

no code implementations8 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.

Q-Learning

Bayesian Persuasion with State-Dependent Quadratic Cost Measures

no code implementations22 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

Reliable Smart Road Signs

no code implementations30 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.

Classification General Classification

Reliable Intersection Control in Non-cooperative Environments

no code implementations22 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.

Team-Optimal Distributed MMSE Estimation in General and Tree Networks

no code implementations3 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.

Predicting Nearly As Well As the Optimal Twice Differentiable Regressor

no code implementations23 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.

regression

A Novel Family of Adaptive Filtering Algorithms Based on The Logarithmic Cost

no code implementations26 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.