Game Theory, Optimization and Multi-Agent Learning


Over the past decade, Machine Learning has delivered important advances in learning challenges such as speech and image recognition, translation, text and image generation, and protein folding. These challenges pertain to single-agent learning problems, involving a single agent whose goal is to use observations from  some unknown environment in order to learn how to make good predictions or decisions in this environment. These problems are typically modeled in the language of  single-objective optimization and solved via simple methods such as gradient descent or some variant of it. From robustifying machine learning models against adversarial attacks to training generative models, to performing causal inference, to playing difficult games like Go, Poker and Starcraft, to improving autonomous driving agents, to evaluating the outcomes of economic policies, to training agents for some multi-agent interaction, many outstanding challenges in Machine Learning pertain to multi-agent learning problems, wherein multiple agents learn and make decisions and predictions in a shared environment. These settings deviate from the single-objective optimization paradigm as different agents may have different objectives, and Game Theory provides a useful framework for thinking about such settings. At the same time, classical Game Theory falls short from addressing the challenges posed by modern ML applications, such as the high-dimensionality of strategies and the non-concavity of utilities/non-convexity of losses that one typically encounters in these settings. We develop the foundations of multi-agent learning, bringing to bear techniques from optimization, game theory and learning.


Alkmini Sgouritsa
University of Liverpool
Aris Moustakas
National Kapodistrian University of Athens
Aris Pagourtzis
National Technical University of Athens
Christos H. Papadimitriou
Columbia University
Christos Tzamos
University of Athens and UW Madison
Constantinos Caramanis
University of Texas, Austin
Constantinos Daskalakis
Dimitris Fotakis
National Technical University of Athens
Evangelos Markakis
Athens University of Economics and Business
Georgios Amanatidis
University of Essex
Georgios Christodoulou
Aristotle University of Thessaloniki
Ioannis Panageas
University of California, Irvine
Panayotis Mertikopoulos
French National Center for Scientific Research (CNRS)
Yang Cai
Yale University

The project “ARCHIMEDES Unit: Research in Artificial Intelligence, Data Science and Algorithms” with code OPS 5154714 is implemented by the National Recovery and Resilience Plan “Greece 2.0” and is funded by the European Union – NextGenerationEU.