Multi-Player Zero-Sum Markov Games with Networked Separable Interactions

Authors: Chanwoo Park, Kaiqing Zhang, Asuman Ozdaglar

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

Reproducibility Variable Result LLM Response
Research Type Experimental We also provide numerical experiments to corroborate our theoretical results.
Researcher Affiliation Academia Chanwoo Park MIT cpark97@mit.edu Kaiqing Zhang University of Maryland, College Park kaiqing@umd.edu Asuman Ozdaglar MIT asuman@mit.edu
Pseudocode Yes The overall dynamics are summarized in Algorithm 4... The overall procedure is summarized in Algorithm 6. ... We propose to study the vanilla Multiplicative Weight Update (MWU) algorithm [55] in the regularized zero-sum NG, as tabulated in Algorithm 9. We have also introduced a variant with diminishing regularization, and summarize the update rule in Algorithm 10.
Open Source Code No The paper does not provide any explicit statement or link for open-source code for the methodology described.
Open Datasets No The paper introduces examples like 'Markov fashion games' and mentions 'numerical experiments', but does not specify the use of any publicly available datasets or provide concrete access information (link, DOI, citation) for data used in training or evaluation.
Dataset Splits No The provided text does not contain specific information about training, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers).
Experiment Setup No The paper does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings.