Persuading Farsighted Receivers in MDPs: the Power of Honesty

Authors: Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Mirco Mutti

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Formally, we design an algorithm that computes an optimal and ϵ-persuasive history-dependent signaling scheme in time polynomial in 1/ϵ and in the instance size. Indeed, differently from most of the MDPs settings, we prove that Markovian signaling schemes are not optimal, and general history-dependent signaling schemes should be considered.
Researcher Affiliation Academia Martino Bernasconi Bocconi University martino.bernasconi@unibocconi.it Matteo Castiglioni Politecnico di Milano matteo.castiglioni@polimi.it Alberto Marchesi Politecnico di Milano alberto.marchesi@polimi.it Mirco Mutti Technion mirco.m@technion.ac.il
Pseudocode Yes Algorithm 1 Sender-receiver interaction, Algorithm 2 From histories to promises, Algorithm 3 Approximation scheme, Algorithm 4 Approximate oracle
Open Source Code No The paper does not provide any statement or link regarding the release of open-source code for the described methodology.
Open Datasets No The paper presents theoretical results and uses a constructed example in Appendix A to illustrate a proof. It does not utilize or refer to any publicly available datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with dataset splits.
Hardware Specification No The paper is theoretical and does not mention any specific hardware used for computations or experiments.
Software Dependencies No The paper describes theoretical algorithms and proofs without specifying any software dependencies with version numbers required for implementation or execution.
Experiment Setup No The paper is theoretical and does not describe empirical experiments, so no experimental setup details like hyperparameters or training configurations are provided.