Learning Regularized Graphon Mean-Field Games with Unknown Graphons

Authors: Fengzhuo Zhang, Vincent Y. F. Tan, Zhaoran Wang, Zhuoran Yang

JMLR 2024 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, the efficacy of the proposed algorithms are corroborated through simulations. These simulations demonstrate that learning the unknown graphons reduces the exploitability effectively. ... In this section, we utilize simulations to demonstrate the importance of learning the underlying graphons, thus corroborating our theoretical results. We simulate our algorithms on the Susceptible-Infectious-Susceptible (SIS) problem and investment problem.
Researcher Affiliation Academia Fengzhuo Zhang EMAIL Department of Electrical and Computer Engineering National University of Singapore Singapore 117583 Vincent Y. F. Tan EMAIL Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Singapore 119076 Zhaoran Wang EMAIL Department of Industrial Engineering and Management Sciences Northwestern University Evanston, IL 60208-3109, USA Zhuoran Yang EMAIL Department of Statistics and Data Science Yale University New Haven, CT 06511, USA
Pseudocode Yes Algorithm 1 GMFG-PPO Procedure: ... Algorithm 2 Estimation of µI t , µI t+1, and Qλ,α h (s, a, πα t , µI t , W)
Open Source Code No The code used in our simulations uses the code in Fabian et al. (2022) and Cui and Koeppl (2021b) for building the simulation environment.
Open Datasets No In this section, we provide the details of our experiments shown in Section 7 of the main paper. We first formally define the SIS and investment problems. ... We simulate our algorithms on the Susceptible-Infectious-Susceptible (SIS) problem and investment problem.
Dataset Splits No The paper describes simulation environments (SIS and investment problems) and how data is collected within these simulations (e.g., 'L trajectories of N sampled agents', 'L independent rounds'). However, it does not refer to a pre-existing dataset with specified training/validation/test splits, as the data is generated based on defined models and parameters.
Hardware Specification Yes We run our simulations on Intel(R) Core(TM) i5-8257U CPU @ 1.40GHz.
Software Dependencies No The code used in our simulations uses the code in Fabian et al. (2022) and Cui and Koeppl (2021b) for building the simulation environment. [No version numbers provided for these or other software.]
Experiment Setup Yes The horizon is H = 50. ... We set θ = 3 for exp-graphon. For SBM graphon, we set K = 2, p0 = 1, p1 = 0.7, p2 = 1, a11 = a22 = 0.9, and a12 = a21 = 0.3. We set a = 1, b = 0.5 for affine attachment graphon and ranked attachment graphon. We set the regularization parameter as λ = 1 in our experiments. ... We only estimate the model in the beginning of the first iteration round and reuse this estimate in the following iterations to generate action-value function estimates. Figures 2, 3 and 4 are derived from twenty Monte-Carlo implementations of the algorithms.