Deep Mean Field Games for Learning Optimal Behavior Policy of Large Populations

By Jiachen Yang, Xiaojing Ye, Rakshit S. Trivedi, Huan Xu, Hongyuan Zha. 2017

37 citations recorded by the source corpus.

We consider the problem of representing a large population's behavior policy that drives the evolution of the population distribution over a discrete state space. A discrete time mean field game (MFG) is motivated as an interpretable model founded on game theory for understanding the aggregate effect of individual actions and predicting the temporal evolution of population distributions. We achieve a synthesis of MFG and Markov decision processes (MDP) by showing that a special MFG is reducible to an MDP. This enables us to broaden the scope of mean field game theory and infer MFG models of large real-world systems via deep inverse reinforcement learning. Our method learns both the reward function and forward dynamics of an MFG from real data, and we report the first empirical test of a mean field game model of a real-world social media population.

Subfields: Sociology and Political Science, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Sociology and Political Science

1. Weinan Zhang
2. Jun Wang

In Statistical and Nonlinear Physics

1. M. Zhou
2. Weinan Zhang
3. Minne Li
4. Jun Wang
5. Yaodong Yang
6. Rui Luo

Citations in the corpus

• Mean Field Multi-Agent Reinforcement Learning (2018, background): “Very recently, Yang et al. (2017) built a connection between MFG and reinforcement learning.”