Game-Theoretic Learning and Distributed Optimization in Memoryless Multi-Agent Systems

by Tatiana Tatarenko

Overview

This book presents new efficient methods for optimization in realistic large-scale, multi-agent systems. These methods do not require the agents to have the full information about the system, but instead allow them to make their local decisions based only on the local information, possibly obtained during communication with their local neighbors. The book, primarily aimed at researchers in optimization and control, considers three different information settings in multi-agent systems: oracle-based, communication-based, and payoff-based. For each of these information types, an efficient optimization algorithm is developed, which leads the system to an optimal state. The optimization problems are set without such restrictive assumptions as convexity of the objective functions, complicated communication topologies, closed-form expressions for costs and utilities, and finiteness of the system’s state space.

Product Details

ISBN-13:	9783319654782
Publisher:	Springer International Publishing
Publication date:	09/21/2017
Edition description:	1st ed. 2017
Pages:	171
Product dimensions:	6.10(w) x 9.25(h) x (d)

About the Author

Tatiana Tatarenko received her Ph.D. from the Control Methods and Robotics Lab at the Technical University of Darmstadt, Germany in 2017. In 2011, she graduated with honors in Mathematics, focusing on statistics and shastic processes, from Lomonosov Moscow State University, Russia. Her main research interests are in the fields of distributed optimization, game-theoretic learning, and shastic processes in networked multi-agent systems. Currently, Dr. Tatarenko is a research assistant at TU Darmstadt, where she teaches and supervises students.

Table of Contents

Introduction and Research Motivation.- Backgrounds and Formulation of Contributions.- Logit Dynamics in Potential Games with Memoryless Players.- Shastic Methods in Distributed Optimization and Game-Theoretic Learning.- Conclusion.- Appendix.

Editorial Reviews

This book offers new efficient methods for optimization and control in multi-agent systems through the agency of game-theoretic learning. … The book represents an important scientific contribution in the field of optimization for the multi-agent systems.” (Vasile Postolică, zbMath 1415.91002, 2019)

From the Publisher