Characterising Simulation-Based Program Equilibria

Authors: Emery Cooper, Caspar Oesterheld, Vincent Conitzer

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we propose a generalisation to Oesterheld s (2019) ϵGroundedπBot. We prove a folk theorem for our programs in a setting with access to a shared source of randomness. We then characterise their equilibria in a setting without shared randomness. Both with and without shared randomness, we achieve a much wider range of equilibria than Oesterheld s (2019) ϵGroundedπBot. Finally, we explore the limits of simulation-based program equilibrium, showing that the Tennenholtz folk theorem cannot be attained by simulation-based programs without access to shared randomness.
Researcher Affiliation Academia Emery Cooper, Caspar Oesterheld, Vincent Conitzer Carnegie Mellon University EMAIL, EMAIL, EMAIL
Pseudocode Yes Algorithm 1 Correlated ϵGroundedπi Bot... Algorithm 2 uncorrelated ϵGroundedπBot
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper describes conceptual game theory scenarios (e.g., Example 1, Table 1, Table 2, Table 3, Table 4) and payoff matrices, but it does not use or provide access information for any publicly available or open datasets for empirical evaluation.
Dataset Splits No Since the paper does not involve empirical experiments using datasets, there is no mention of dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any empirical experiments, thus no hardware specifications for running experiments are provided.
Software Dependencies No The paper is theoretical and does not describe any empirical experiments, thus no specific software dependencies with version numbers are mentioned for replication.
Experiment Setup No The paper is theoretical and does not describe any empirical experiments, thus no specific experimental setup details such as hyperparameters or training configurations are provided.