Online Bayesian Persuasion

Authors: Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical First, we prove a hardness result on the per-round running time required to achieve no-α-regret for any α < 1. Then, we provide algorithms for the full and partial feedback models with regret bounds sublinear in the number of rounds and polynomial in the size of the instance.
Researcher Affiliation Collaboration Matteo Castiglioni Politecnico di Milano matteo.castiglioni@polimi.it Andrea Celli Facebook Core Data Science andreacelli@fb.com Alberto Marchesi Politecnico di Milano alberto.marchesi@polimi.it Nicola Gatti Politecnico di Milano nicola.gatti@polimi.it
Pseudocode Yes Algorithm 1 ONLINE BAYESIAN PERSUASION WITH PARTIAL INFORMATION FEEDBACK
Open Source Code No The paper does not contain any statement about making its source code available or provide any links to a code repository.
Open Datasets No The paper is theoretical and does not involve experiments with datasets, thus no information about public datasets is provided.
Dataset Splits No The paper focuses on theoretical algorithms and their regret bounds, not empirical evaluation. Therefore, it does not discuss training/validation/test dataset splits.
Hardware Specification No The paper presents theoretical work and does not report on experiments, thus no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training configurations.