181 citations · 321 across the 23 of their papers we have counts for
12 papers · 1 filter
Convergence of Heterogeneous Learning Dynamics in Zero-sum Stochastic Games
Yuksel Arslantas, Ege Yuceel, Yigit Yalin +1
This paper presents new families of algorithms for the repeated play of two-agent (near) zero-sum games and two-agent zero-sum stochastic games. For example, the family includes fi…
Finite-horizon Approximations and Episodic Equilibrium for Stochastic Games
Muhammed O. Sayin
This paper proposes a finite-horizon approximation scheme and introduces episodic equilibrium as a solution concept for stochastic games (SGs), where agents strategize based on the…
Episodic Logit-Q Dynamics for Efficient Learning in Stochastic Teams
Onur Unlu, Muhammed O. Sayin
We present new learning dynamics combining (independent) log-linear learning and value iteration for stochastic games within the auxiliary stage game framework. The dynamics presen…
Logit-Q Dynamics for Efficient Learning in Stochastic Teams
Ahmed Said Donmez, Onur Unlu, Muhammed O. Sayin
We present a new family of logit-Q dynamics for efficient learning in stochastic games by combining the log-linear learning (also known as logit dynamics) for the repeated play of…
Fictitious Play in Markov Games with Single Controller
Muhammed O. Sayin, Kaiqing Zhang, Asuman Ozdaglar
Certain but important classes of strategic-form games, including zero-sum and identical-interest games, have the fictitious-play-property (FPP), i.e., beliefs formed in fictitious…
Episodic Logit-Q Dynamics for Efficient Learning in Stochastic Teams
Onur Unlu, Muhammed O. Sayin
We present new learning dynamics combining (independent) log-linear learning and value iteration for stochastic games within the auxiliary stage game framework. The dynamics presen…
On the Global Convergence of Stochastic Fictitious Play in Stochastic Games with Turn-based Controllers
Muhammed O. Sayin
This paper presents a learning dynamic with almost sure convergence guarantee for any stochastic game with turn-based controllers (on state transitions) as long as stage-payoffs in…
Independent Learning in Stochastic Games
Asuman Ozdaglar, Muhammed O. Sayin, Kaiqing Zhang
Reinforcement learning (RL) has recently achieved tremendous successes in many artificial intelligence applications. Many of the forefront applications of RL involve multiple agent…
Decentralized Q-Learning in Zero-sum Markov Games
Muhammed O. Sayin, Kaiqing Zhang, David S. Leslie +2
We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, wh…
Fictitious play in zero-sum stochastic games
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…
Bayesian Persuasion with State-Dependent Quadratic Cost Measures
Muhammed O. Sayin, Tamer Basar
We address Bayesian persuasion between a sender and a receiver with state-dependent quadratic cost measures for general classes of distributions. The receiver seeks to make mean-sq…
Hierarchical Multistage Gaussian Signaling Games in Noncooperative Communication and Control Systems
Muhammed O. Sayin, Emrah Akyol, Tamer Basar
We analyze in this paper finite horizon hierarchical signaling games between (information provider) senders and (decision maker) receivers in a dynamic environment. The underlying…