Learning Discrete-Time Major-Minor Mean Field Games
Authors: Kai Cui, Gökçe Dayanıklı, Mathieu Laurière, Matthieu Geist, Olivier Pietquin, Heinz Koeppl
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our theoretical investigation verifies both the M3FG model and its algorithmic solution... Then, we empirically verify the obtained theoretical results, ablating some of the theoretical assumptions made, and show successful equilibrium learning in three example problems. |
| Researcher Affiliation | Collaboration | Kai Cui*1, G okc e Dayanıklı*2, Mathieu Lauri ere3, Matthieu Geist4, Olivier Pietquin5, Heinz Koeppl1 1Technische Universit at Darmstadt, 2University of Illinois at Urbana-Champaign, 3NYU Shanghai, 4Google Deep Mind, 5Cohere |
| Pseudocode | Yes | Algorithm 1: Discrete-time, projected fictitious play |
| Open Source Code | Yes | For code, see https://github.com/tud-kcui/M3FG-learning. |
| Open Datasets | No | For the evaluation, we use the following problem instances for exemplary, practically applicable M3FG scenarios. SIS epidemics control. ... Buffet problem. ... Advertisement duopoly model. The paper describes these as problem instances or models rather than referencing pre-existing, publicly available datasets with access information. |
| Dataset Splits | No | The paper describes the problem instances used for evaluation (SIS epidemics control, Buffet problem, Advertisement duopoly model), but does not specify any training, validation, or test dataset splits (e.g., percentages or sample counts) as it appears to be based on simulated environments rather than pre-existing datasets with fixed splits. |
| Hardware Specification | No | The authors acknowledge the Lichtenberg high performance computing cluster of the TU Darmstadt for providing computational facilities for the calculations of this research. This statement refers to a high-performance computing resource but lacks specific hardware details such as CPU/GPU models, memory, or processor types. |
| Software Dependencies | No | The paper does not provide specific version numbers for software components or libraries (e.g., Python, PyTorch, or specific solvers) used in the experiments. |
| Experiment Setup | No | The paper states: 'Additional experiments and parameter details are shown in Cui et al. (2023, Appendix I)', indicating that such details are provided in a separate preprint appendix, not within the main body of this paper. |