Learning Regularized Monotone Graphon Mean-Field Games

Authors: Fengzhuo Zhang, Vincent Tan, Zhaoran Wang, Zhuoran Yang

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

Reproducibility Variable Result LLM Response
Research Type Experimental The efficiency of the designed algorithm is corroborated by empirical evaluations.In this section, we conduct experiments to corroborate our theoretical findings.
Researcher Affiliation Academia 1National University of Singapore 2 Northwestern University 3Yale University
Pseudocode Yes Algorithm 1 Mono GMFG-PMD Procedure: and Algorithm 2 Estimation of Action-value Function Procedure:
Open Source Code No The paper does not provide an explicit statement or a link to open-source code for the methodology described.
Open Datasets Yes We run different algorithms on the Beach Bar problem Perrin et al. [2020], Fabian et al. [2022].
Dataset Splits No The paper describes sampling N agents and collecting data from K episodes for its experiments but does not provide specific train/validation/test dataset splits, such as percentages or sample counts.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper mentions parameters like N (number of sampled players) and K (number of episodes) used in experiments, and states that 'The details of experiments are deferred to Appendix B.', but does not provide specific hyperparameter values (e.g., learning rate, batch size, optimizer settings) in the main text.