Deep Reinforcement Learning for Robust Agent Systems

Erscheinungsjahr 2026
ISBN: 978-981-9260-70-6
Verlag: Springer

Buch, Englisch, 249 Seiten, Format (B × H): 155 mm x 235 mm

Deep Reinforcement Learning for Single-/Multi-Agent Systems provides a comprehensive guide to understanding and applying reinforcement learning (RL) in both single-agent and multi-agent contexts. This book is ideal for readers interested in mastering the fundamental concepts of RL and its advanced applications in real-world scenarios. Whether you’re a researcher, developer, or student, it offers a unique blend of theoretical depth and practical insights to empower you in tackling complex problems in AI and autonomous systems.

The book begins with foundational topics in RL, explaining key algorithms and methods for both single-agent and multi-agent systems. It then dives into robust reinforcement learning, focusing on adversarial attacks and defense techniques to improve model resilience in uncertain environments. The content also covers cutting-edge applications of RL, including the design of training environments, the deployment of RL in drone systems, and the integration of RL in large language models (LLMs).

By reading this book, you will gain valuable knowledge about state-of-the-art RL methodologies, learn to apply them in diverse settings, and understand how to defend against adversarial threats. The practical examples, case studies, and code snippets make it easier to implement RL solutions, while the in-depth discussions provide a solid foundation for further research. Prerequisite knowledge in machine learning and basic programming will be helpful, but the book is accessible to anyone with a keen interest in AI and reinforcement learning.

Zielgruppe

Research

Autoren/Hrsg.

Liu, Guanjun

Zhou, Ziyuan

Yang, Min

Guo, Weiran

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen

Inhaltsverzeichnis

Chapter 1. Theoretical Foundations of Deep Reinforcement Learning.- Chapter 2. Algorithms of Single-Agent Reinforcement Learning.- Chapter 3. Algorithms of Multi-Agent Reinforcement Learning.- Chapter 4. Robustness on Single-Agent Reinforcement Learning.- Chapter 5. Robustness on Multi-Agent Reinforcement Learning.- Chapter 6. Training Environments of Reinforcement Learning.- Chapter 7. Applications of Deep Reinforcement Learning in Unmanned Aerial Vehicle and Autonomous Driving.- Chapter 8. Application of Deep Reinforcement Learning in Large Language Model.

Über Autor(innen)

Guanjun Liu received the Ph.D. degree in Computer Software and Theory from Tongji University, China, in 2011. He was a post-doctoral research fellow with the Singapore University of Technology and Design, Singapore, from 2011 to 2013, and a post-doctoral research fellow with the Humboldt University of Berlin, Germany, from 2013 to 2014, supported by the Alexander von Humboldt Foundation. He is currently a professor with the School of Computer Science and Technology, Tongji University. His research interests include multi-agent systems, reinforcement learning, machine learning, cyber-physical systems, UAV, Petri net theory, model checking, credit-card fraud detection, and real-time concurrent systems. He has authored over 160 papers and 4 monographs. He served as program committees for a dozen of international conferences and an associate editor of . He is a senior member of IEEE.

Ziyuan Zhou received the Ph.D. degree in computer science from Tongji University, Shanghai, China, in 2025. During her doctoral studies, she was a joint Ph.D. student with the Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA. She is currently a researcher at Shanghai Artificial Intelligence Laboratory, Shanghai, China. Her research interests include reinforcement learning, multi-agent systems, trustworthy artificial intelligence, and large language models.

Min Yang is currently pursuing a Ph.D. in computer science and technology at Tongji University in Shanghai. Her research interests include reinforcement learning, multi-agent systems, and system verification and testing.

Weiran Guo received the B.S. degree in information security from Tongji University, Shanghai, China, in 2023, and the M.S. degree in computer software and theory from Tongji University in 2026. She is currently a researcher at XPENG Robotics, where she focuses on large language models, agentic reinforcement learning, and embodied intelligent systems. Her research interests include reinforcement learning, multi-agent systems, safe reinforcement learning, reinforcement learning for large language models, intelligent agents, and embodied AI.