Online Learning of Coalition Structures by Selfish Agents

Authors: Saar Cohen, Noa Agmon

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main result is a sample-efficient algorithm for selfish agents that aims to minimize their Nash regret under both semi-bandit and bandit feedback, implying approximately Nash stable outcomes. Under both feedback settings, our algorithm enjoys Nash regret and sample complexity bounds that are optimal up to logarithmic factors.
Researcher Affiliation Academia Saar Cohen, Noa Agmon Department of Computer Science, Bar-Ilan University, Israel EMAIL, EMAIL
Pseudocode Yes Algorithm 1: UCB-NS Algorithm 2: ε-BRD
Open Source Code No The paper mentions supplementary materials for proofs, but there is no explicit statement about releasing source code, a repository link, or code being available in supplementary materials for the methodology described.
Open Datasets No The paper uses a conceptual 'study groups example' to illustrate the problem but does not describe or refer to any specific dataset used for empirical evaluation of the proposed algorithms. There are no links, DOIs, or citations to any datasets.
Dataset Splits No The paper does not conduct empirical experiments using specific datasets. Therefore, there is no mention of dataset splits for training, validation, or testing.
Hardware Specification No The paper focuses on theoretical algorithm design and analysis, including Nash regret and sample complexity bounds. It does not describe any experimental setup, thus no specific hardware specifications are mentioned.
Software Dependencies No The paper proposes algorithms (UCB-NS, ε-BRD) and provides theoretical analysis. It does not mention any specific software packages, libraries, or their version numbers that would be required to implement or reproduce the work.
Experiment Setup No The paper is theoretical and focuses on algorithm design and analysis. It does not describe any empirical experiments, and therefore no specific experimental setup details, such as hyperparameters or training configurations, are provided.