Publications

Multi-Agent Reinforcement Learning

Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
with Fivos Kalogiannis, Ioannis Anagnostides, Ioannis Panageas, Emmanouil-Vasileios Vlatakis-Gkaragkounis and Vaggos Chatziafratis
ICLR 2023 (Oral talk)

Reinforcement Learning for Location-Aware Scheduling
with Biswa Sengupta
ICLR 2022 Generalizable Policy Learning in the Physical World Workshop

Game Theory

Beating Price of Anarchy and Gradient Descent without Regret in Potential Games
with Iosif Sakos, Stefanos Leonardos, William Overman, Ioannis Panageas and Georgios Piliouras
ICLR 2024

Computing Nash Equilibria in Potential Games with Private Uncoupled Constraints
with Nikolas Patris, Fivos Kalogiannis, Rose Zhang and Ioannis Panageas
AAAI 2024

Privacy-Aware Reinforcement Learning

adaParl : Adaptive Privacy-Aware Reinforcement Learning for Sequential-Decision Making Human-in-the-Loop Systems
with Mojtaba Taherisadr and Salma Elmalaki
IoTDI’23

Expressivity of Neural Networks

On Scrambling Phenomena for Randomly Initialized Recurrent Networks
with Vaggos Chatziafratis, Ioannis Panageas and Clayton Sanford
NeurIPS 2022