Online Bayesian Persuasion Without a Clue

Authors: Francesco Bacchiocchi, Matteo Bollini, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical 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-relevant information. ... We design an algorithm that achieves sublinear in the number of rounds regret with respect to an optimal signaling scheme, and we also provide a collection of lower bounds showing that the guarantees of such an algorithm are tight.
Researcher Affiliation Academia Francesco Bacchiocchi Politecnico di Milano francesco.bacchiocchi@polimi.it Matteo Bollini Politecnico di Milano matteo.bollini@polimi.it Matteo Castiglioni Politecnico di Milano matteo.castiglioni@polimi.it Alberto Marchesi Politecnico di Milano alberto.marchesi@polimi.it Nicola Gatti Politecnico di Milano nicola.gatti@polimi.it
Pseudocode Yes Algorithm 1 Learn-to-Persuade-w/o-Clue
Open Source Code No The paper does not mention releasing any source code for its methodology.
Open Datasets No The paper is theoretical and does not use or mention any datasets.
Dataset Splits No The paper is theoretical and does not involve dataset splits.
Hardware Specification No The paper is theoretical and does not mention any hardware specifications for experiments.
Software Dependencies No The paper is theoretical and does not list any specific software dependencies or versions.
Experiment Setup No The paper is theoretical and does not describe an experimental setup or hyperparameters.