Convergence of Heterogeneous Learning Dynamics in Zero-sum Stochastic Games
Published in IEEE TAC, 2025
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.
Publications
Vulnerability Assessment of Reinforcement Learning in Stochastic Security Games
Published in 😊, 2024
This paper investigates the vulnerability of RL (specifically independent Q-learning) algorithms used for defense in the context of stochastic security games with linear influence networks.
Strategic Control of Experience-Weighted Attraction Model in Human-AI Interactions
Published in IFAC CPHS, 2024
This paper investigates a novel control framework for strategic Artificial Intelligence (AI) in human interactions. We leverage the Experience-Weighted Attraction (EWA) model, a widely used method for capturing human learning dynamics.
Strategizing against Q-learners: A Control-theoretical Approach
Published in IEEE L-CSS, 2024
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.
Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
Published in NeurIPS, 2024
This paper presents a new variant of fictitious play (FP) called team-fictitious-play (Team-FP) that can reach equilibrium in multi-team competition.