Research

Authors Diego Piccinotti, Amarildo Likmeta, Nicolò Brunello, Marcello Restelli Abstract Formula 1 (F1) racing is one of the most competitive racing competitions involving high-performance single-seater racing vehicles. The result of a race is determined by vehicle and driver performance, as well as by the tire and pit-stop strategy employed in the race. In this work, […]

Authors Alberto Maria Metelli, Alessio Russo, Marcello Restelli Abstract Importance Sampling (IS) is a widely used building block for a large variety of off-policy estimation and learning algorithms. However, empirical and theoretical studies have progressively shown that vanilla IS leads to poor estimations whenever the behavioral and target policies are too dissimilar. In this paper, […]

Authors Alberto Maria Metelli, Matteo Pirotta, Daniele Calandriello, Marcello Restelli Abstract This paper presents a study of the policy improvement step that can be usefully exploited by approximate policy–iteration algorithms. When either the policy evaluation step or the policy improvement step returns an approximated result, the sequence of policies produced by policy iteration may not […]

Authors Carlo D’Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters Abstract MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments. Compared to other available libraries, MushroomRL has been created with the purpose of providing a comprehensive and flexible framework to minimize the effort in […]

Authors Martino Bernasconi, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Alberto Marchesi, Francesco Trovò Abstract Recently, game-playing agents based on AI techniques have demonstrated super-human performance in several sequential games, such as chess, Go, and poker. Surprisingly, the multi-agent learning techniques that allowed to reach these achievements do not take into account the actual behavior of […]

Authors Martino Bernasconi, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Francesco Trovò Abstract In this paper, we study the mean dynamics of the soft-max policy gradient algorithm in multi-agent settings by resorting to evolutionary game theory and dynamical system tools. Such a study is crucial to understand the algorithm’s weaknesses when employed in multi-agent settings. Unlike […]

Authors Matteo Castiglioni, Alberto Marchesi, NicolaGatti Abstract We address multi-agent Stackelberg settings involving many leaders and followers. In order to effectively model this kind of interactions, we extend the idea of commitment to correlated strategies to Stackelberg games with multiple leaders and followers. Correlation can be easily implemented by resorting to a device that sends signals to the players, […]

Authors Matteo Castiglioni, Diodato Ferraioli, Nicola Gatti, Giulia Landriani Abstract We focus on the election manipulation problem through social influence, where a manipulator exploits a social network to make her most preferred candidate win an election. Influence is due to information in favor of and/or against one or multiple candidates, sent  by seeds and spreading […]

Authors Matteo Castiglioni, Alberto Marchesi, Nicola Gatti Abstract We study principal-agent problems in which a principal commits to an outcome-dependent payment scheme (a.k.a. contract) so as to induce an agent to take a costly, unobservable action. We relax the assumption that the principal perfectly knows the agent by considering a Bayesian setting where the agent’s […]

Authors Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm Abstract We focus on the problem of finding an optimal strategy for a team of players that faces an opponent in an imperfect-information zero-sum extensive-form game. Team members are not allowed to communicate during play but can coordinate before the game. In this setting, it is […]