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

Tatarenko, Tatiana

Hardcover

ISBN 10: 3319654780 ISBN 13: 9783319654782

Publisher: Springer, 2017

Synopsis

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. 

About this title

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 stochastic processes, from Lomonosov Moscow State University, Russia. Her main research interests are in the fields of distributed optimization, game-theoretic learning, and stochastic processes in networked multi-agent systems. Currently, Dr. Tatarenko is a research assistant at TU Darmstadt, where she teaches and supervises students. 

From the Back Cover

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 scommunication 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. 

Edition details

• Publisher: Springer
• Publication date: 2017
• ISBN 10: 3319654780
• ISBN 13: 9783319654782
• Binding: Hardcover
• Language: English
• Edition number: 1
• Number of pages: 180