Commitment Games with Conditional Information Disclosure

Authors: Anthony DiGiovanni, Jesse Clifton

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove a folk theorem for this setting that provides sufficient conditions for ex post efficiency, and thus represents a model of ideal cooperation between agents without a third-party mediator. Further, extending previous work on program equilibrium, we develop an implementation of conditional information disclosure. We show that this implementation forms program ϵ-Bayesian Nash equilibria corresponding to the Bayesian Nash equilibria of these commitment games.
Researcher Affiliation Industry Anthony Di Giovanni*, Jesse Clifton* Center on Long-Term Risk, London, UK {anthony.digiovanni, jesse.clifton}@longtermrisk.org
Pseudocode Yes Algorithm 1: ϵGrounded Fair SIRBot
Open Source Code No The paper states, "it is an open question how to implement ϵGrounded Fair SIRBot in machine learning," and does not provide any links to source code or state that code will be released.
Open Datasets No This is a theoretical paper that introduces a game framework and proofs. It does not use or evaluate on datasets, and therefore no information about public dataset access is relevant or provided.
Dataset Splits No This is a theoretical paper that introduces a game framework and proofs. It does not describe empirical experiments with dataset splits for training, validation, or testing.
Hardware Specification No This is a theoretical paper that describes a framework and algorithms. It does not involve running experiments that would require specific hardware, and thus no hardware specifications are provided.
Software Dependencies No This is a theoretical paper that describes a framework and algorithms. It does not involve a specific implementation or experiments that would require detailing software dependencies with version numbers.
Experiment Setup No This is a theoretical paper that introduces a game framework and algorithms. It does not describe any empirical experiments, and therefore no experimental setup details like hyperparameters or system-level training settings are provided.