4 papers
Replicable Constrained Bandits
Matteo Bollini, Gianmarco Genalti, Francesco Emanuele Stradi +2
Algorithmic \emph{replicability} has recently been introduced to address the need for reproducible experiments in machine learning. A \emph{replicable online learning} algorithm is…
Learning in Bayesian Stackelberg Games With Unknown Follower's Types
Matteo Bollini, Francesco Bacchiocchi, Samuel Coutts +2
We study online learning in Bayesian Stackelberg games, where a leader repeatedly interacts with a follower whose unknown private type is independently drawn at each round from an…
Online Bayesian Persuasion Without a Clue
Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni +2
We study online Bayesian persuasion problems in which an informed sender repeatedly faces a receiver with the goal of influencing their behavior through the provision of payoff-rel…
Contracting With a Reinforcement Learning Agent by Playing Trick or Treat
Matteo Bollini, Francesco Bacchiocchi, Matteo Castiglioni +2
We study principal-agent problems where a farsighted agent takes costly actions in an MDP. The core challenge in these settings is that agent's actions are hidden to the principal,…