kmlcube

AAAI-Logo

Exploiting Opponents under Utility Constraints in Extensive-Form Games

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 […]
Read More
AAAI-Logo

The Evolutionary Dynamics of Soft-Max Policy Gradient in Games

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 […]
Read More
Artificial-Intelligence-Cover

Committing to correlated strategies with multiple leaders

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, […]
Read More
JAIR-logo

Election Manipulation on Social Networks: Seeding, Edge Removal, Edge Addition

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 […]
Read More
Artificial-Intelligence-Cover

Bayesian Agency: Linear versus Tractable Contracts

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 […]
Read More
PMLR

Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results

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 […]
Read More
PMLR

Multi-Receiver Online Bayesian Persuasion

Authors Matteo Castiglioni, Alberto Marchesi, Andrea Celli, Nicola Gatti Abstract Bayesian persuasion studies how an informed sender should partially disclose information to influence the behavior of a self-interested receiver. Classical models make the stringent assumption that the sender knows the receiver’s utility. This can be relaxed by considering an online learning framework in which the sender repeatedly faces […]
Read More
AAAI-Logo

Bayesian Persuasion in Online Settings

Authors Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti Abstract In Bayesian persuasion, an informed sender has to design a signaling scheme that discloses the right amount of information so as to influence the behavior of a self-interested receiver. This kind of strategic interaction is ubiquitous in realworld economic scenarios. However, the seminal model by […]
Read More

Configurable Environments in Reinforcement Learning: An Overview

Author Alberto Maria Metelli Abstract Reinforcement Learning (RL) has emerged as an effective approach to address a variety of complex control tasks. In a typical RL problem, an agent interacts with the environment by perceiving observations and performing actions, with the ultimate goal of maximizing the cumulative reward. In the traditional formulation, the environment is […]
Read More
AGU_FallMeeting21

Advancing drought monitoring via feature extraction

Authors Alberto Metelli, Andrea Castelletti, Marcello Restelli. Abstract A drought is a slowly developing natural phenomenon that can occur in all climatic zones and can be defined as a temporary but significant decrease in water availability. Over the past three decades, the cost of droughts in Europe has amounted to over 100 billion euros and […]
Read More