Learning for Decision and Control in Stochastic Networks

Beschreibung

This book introduces the Learning-Augmented Network Optimization (LANO) paradigm, which interconnects network optimization with the emerging AI theory and algorithms and has been receiving a growing attention in network research. The authors present the topic based on a general stochastic network optimization model, and review several important theoretical tools that are widely adopted in network research, including convex optimization, the drift method, and mean-field analysis. The book then covers several popular learning-based methods, i.e., learning-augmented drift, multi-armed bandit and reinforcement learning, along with applications in networks where the techniques have been successfully applied. The authors also provide a discussion on potential future directions and challenges.
This book introduces the Learning-Augmented Network Optimization (LANO) paradigm, which interconnects network optimization with the emerging AI theory and algorithms and has been receiving a growing attention in network research. The authors present the topic based on a general stochastic network optimization model, and review several important theoretical tools that are widely adopted in network research, including convex optimization, the drift method, and mean-field analysis. The book then covers several popular learning-based methods, i.e., learning-augmented drift, multi-armed bandit and reinforcement learning, along with applications in networks where the techniques have been successfully applied. The authors also provide a discussion on potential future directions and challenges.
Introduces Learning-Augmented Network Optimization based on a general stochastic network optimization model Covers key theoretical tools for network research, as well as popular learning-based methods and their applications Discusses potential future directions and challenges related to Learning-Augmented Network Optimization

Autor*in

Longbo Huang

Themen in »Learning for Decision and Control in Stochastic Networks«

Network Optimization Learning Drift Method Convex Optimization Mean-Field Online Learning Reinforcement Learning

Stimmen zu »Learning for Decision and Control in Stochastic Networks«

“This monograph gives an overview of a class of algorithms for optimization of queuing networks in wireless and related networks. … This is followed by approaches based on multi-armed bandits and the approaches that use standard reinforcement learning algorithms grounded in the underlying Markov decision theoretic framework. It concludes with some pointers for future work.” (Vivek S. Borkar, Mathematical Reviews, August, 2024)

Details

Link teilen