Learning Cooperative Mean Field Games on Sparse Chung-Lu Graphs
Keywords: Cooperative Mean Field Games, Large Networks, Sparse Graphs, Multi Agent Reinforcement Learning
TL;DR: We propose a novel cooperative mean field game model on very sparse graphs and design corresponding learning algorithms to solve otherwise intractable multi agent reinforcement learning problems on realistic networks.
Abstract: Large agent networks are abundant in applications and nature and pose difficult challenges in the field of multi-agent reinforcement learning (MARL) due to their computational and theoretical complexity. While graphon mean field games and their extensions provide efficient learning algorithms for dense and moderately sparse agent networks, the case of realistic sparser graphs remains largely unsolved. Thus, we propose a novel cooperative mean field game (MFG) model based on the large class of Chung-Lu graphs including power law networks with coefficients above two. Besides a theoretical analysis, we design scalable learning algorithms which especially apply to the challenging class of graph sequences with finite first moment and infinite second moment. We compare our model and algorithms for various examples on synthetic and real world networks with MFG algorithms based on Lp graphons and graphexes. As it turns out, our approach outperforms existing methods in many examples and on various networks due to the special design aiming at an important, but so far hard to solve class of MARL problems.
Primary Area: learning on graphs and other geometries & topologies
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7106
Loading