4 papers
Equilibrium in Multi-Agent Reinforcement Learning
Maurizio D'Andrea, Bar Light
Standard solution concepts for stochastic games, such as Markov perfect equilibrium and Markov coarse correlated equilibrium, are computationally difficult, and thus, standard dece…
Strategic Queues with Priority Classes
Maurizio D'Andrea, Marco Scarsini
We consider a strategic M/M/1 queueing model under a first-come-first-served regime, where customers are split into two classes and class has priority over class . Customers…
Games played by Exponential Weights Algorithms
Maurizio d'Andrea, Fabien Gensbittel, Jérôme Renault
This paper studies the last-iterate convergence properties of the exponential weights algorithm with constant learning rates. We consider a repeated interaction in discrete time, w…
Playing against no-regret players
Maurizio D 'Andrea
In increasingly different contexts, it happens that a human player has to interact with artificial players who make decisions following decision-making algorithms. How should the h…