Skip to main content Skip to main navigation

Publikation

Reinforcement learning algorithms: analysis and applications

Boris Belousov; Hany Abdulsamad; Pascal Klink; Simone Parisi; Jan Peters
Springer, 2021.

Zusammenfassung

This book grew out of a lecture course on reinforcement learning held by Prof. Jan Peters in the winter semester 2018/2019 at Technische Universität Darmstadt. Student research papers covering in depth most prominent research directions in reinforcement learning constitute the core of this volume. Each chapter of the book provides an overview of a specific topic considered in the lecture, with the parts of the book corresponding to big overarching themes in rein- forcement learning. The first part is devoted to the connections with psychology and reward signals in nature. The second part focuses on information-geometric aspects of policy optimization algorithms. The third part covers model-free actor-critic methods, which combine value-based and policy-based algorithms to achieve a better bias-variance trade-off. The fourth part describes model-based approaches, which hold the promise to be more sample-efficient than their model-free counterparts. The board of editors consists of doctoral students and research assistants at TU Darmstadt headed by Prof. Jan Peters. Each part of the book was reviewed and edited by specialists in the corresponding research area. The book is intended for machine learning and reinforcement learning students and researchers. Knowledge of linear algebra and statistics is desirable. Nevertheless, all key concepts are introduced in each respective part and chapter of the book, keeping the presentation self-contained and accessible. We would like to thank our colleagues who helped in organizing the course and assisted in supervising the student research projects: Dr. Riad Akrour, Dr. Joni Pajarinen, Oleg Arenz, Daniel Tanneberg, Svenja Stark, Fabio Muratore, Samuele Tosatto, and Michael Lutter. Last but not least, we thank our families and friends who supported and encouraged us at all stages of this project.