Huawei – Hirp Explorary : Machine Learning and mean field game in the field of telecommunications

Scientific project

Mathematical mean field approaches play an important role in different fields of physics, chemistry, biology… but have found in recent works their applications in engineering, economics, finance and game theory.
We first overview some existing works (continuum of states as well as finite number of individual states) in different fields. One of common ideas of these works on mean field is to replace ail interactions to any one player with an aggregate or effective interaction under some assumptions. This reduces any multi-players (but large) problem into an effective few parameter problem. The main idea in ail these works is about the impact of the aggregate of the system in terms of the contribution of each individual.