WEP 2014 - Distributed Strategic Learning by Dr. Hamidou Tembine

Overview

Abstract

This course will introduce the audience to some of the essential ingredients of learning in games under uncertainty (random matrix games), particularly reinforcement learning, cost-of-learning, Q-learning, mean-field learning, combined learning, heterogeneous learning and hybrid learning. The course will emphasize a stochastic approximation approach and will present one of the major challenges in the design of large-scale systems: the need for fully distributed learning algorithm schemes that consume a minimal amount of resources with a minimal amount of information exchange and yet with a very fast convergence time.​