5 papers
Actor-Dual-Critic Dynamics for Zero-sum and Identical-Interest Stochastic Games
Ahmed Said Donmez, Yuksel Arslantas, Muhammed O. Sayin
We propose a novel independent and payoff-based learning framework for stochastic games that is model-free, game-agnostic, and gradient-free. The learning dynamics follow a best-re…
Omniscient Attacker in Stochastic Security Games with Interdependent Nodes
Yuksel Arslantas, Ahmed Said Donmez, Ege Yuceel +1
The adoption of reinforcement learning for critical infrastructure defense introduces a vulnerability where sophisticated attackers can strategically exploit the defense algorithm'…
Strategizing against Q-learners: A Control-theoretical Approach
Yuksel Arslantas, Ege Yuceel, Muhammed O. Sayin
In this paper, we explore the susceptibility of the independent Q-learning algorithms (a classical and widely used multi-agent reinforcement learning method) to strategic manipulat…
Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
Ahmed Said Donmez, Yuksel Arslantas, Muhammed O. Sayin
Multi-team games, prevalent in robotics and resource management, involve team members striving for a joint best response against other teams. Team-Nash equilibrium (TNE) predicts t…
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…