Statistical Reinforcement Learning
Modern Machine Learning Approaches
1st Edition
Published on 16. March 2015
206 pages
978-1-040-05815-2 (ISBN)
Description
Reinforcement learning (RL) is a framework for decision making in unknown environments based on a large amount of data. Several practical RL applications for business intelligence, plant control, and gaming have been successfully explored in recent years. Providing an accessible introduction to the field, this book covers model-based and model-free approaches, policy iteration, and policy search methods. It presents illustrative examples and state-of-the-art results, including dimensionality reduction in RL and risk-sensitive RL. The book provides a bridge between RL and data mining and machine learning research.
Reviews / Votes
This book by Prof. Masashi Sugiyama covers the range of reinforcement learning algorithms from a fresh, modern perspective. With a focus on the statistical properties of estimating parameters for reinforcement learning, the book relates a number of different approaches across the gamut of learning scenarios.... It is a contemporary and welcome addition to the rapidly growing machine learning literature. Both beginner students and experienced researchers will find it to be an important source for understanding the latest reinforcement learning techniques.-Daniel D. Lee, GRASP Laboratory, School of Engineering and Applied Science, University of PennsylvaniaMore details
Series
Edition
1. Auflage
Language
English
Place of publication
London
United Kingdom
Publishing group
Taylor & Francis Ltd
Target group
Professional and scholarly
ISBN-13
978-1-040-05815-2 (9781040058152)
Copyright in bibliographic data and cover images is held by Nielsen Book Services Limited or by the publishers or by their respective licensors: all rights reserved.
Schweitzer Classification
Other editions
Additional editions
Book
06/2020
1st Edition
Chapman & Hall/CRC
€69.10
Shipment within 15-20 days
Book
03/2015
1st Edition
Chapman & Hall/CRC
€121.10
Shipment within 15-20 days
Person
Masashi Sugiyama received his bachelor, master, and doctor of engineering degrees in computer science from the Tokyo Institute of Technology, Japan. In 2001 he was appointed assistant professor at the Tokyo Institute of Technology and he was promoted to associate professor in 2003. He moved to the University of Tokyo as professor in 2014.
He received an Alexander von Humboldt Foundation Research Fellowship and researched at Fraunhofer Institute, Berlin, Germany, from 2003 to 2004. In 2006, he received a European Commission Program Erasmus Mundus Scholarship and researched at the University of Edinburgh, Scotland. He received the Faculty Award from IBM in 2007 for his contribution to machine learning under non-stationarity, the Nagao Special Researcher Award from the Information Processing Society of Japan in 2011, and the Young Scientists' Prize from the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology for his contribution to the density-ratio paradigm of machine learning.
His research interests include theories and algorithms of machine learning and data mining, and a wide range of applications such as signal processing, image processing, and robot control. He published Density Ratio Estimation in Machine Learning (Cambridge University Press, 2012) and Machine Learning in Non-Stationary Environments: Introduction to Covariate Shift Adaptation (MIT Press, 2012).
He received an Alexander von Humboldt Foundation Research Fellowship and researched at Fraunhofer Institute, Berlin, Germany, from 2003 to 2004. In 2006, he received a European Commission Program Erasmus Mundus Scholarship and researched at the University of Edinburgh, Scotland. He received the Faculty Award from IBM in 2007 for his contribution to machine learning under non-stationarity, the Nagao Special Researcher Award from the Information Processing Society of Japan in 2011, and the Young Scientists' Prize from the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology for his contribution to the density-ratio paradigm of machine learning.
His research interests include theories and algorithms of machine learning and data mining, and a wide range of applications such as signal processing, image processing, and robot control. He published Density Ratio Estimation in Machine Learning (Cambridge University Press, 2012) and Machine Learning in Non-Stationary Environments: Introduction to Covariate Shift Adaptation (MIT Press, 2012).
Content
Introduction to Reinforcement Learning. Model-Free Policy Iteration. Policy Iteration with Value Function Approximation. Basis Design for Value Function Approximation. Sample Reuse in Policy Iteration. Active Learning in Policy Iteration. Robust Policy Iteration. Model-Free Policy Search. Direct Policy Search by Gradient Ascent. Direct Policy Search by Expectation-Maximization. Policy-Prior Search. Model-Based Reinforcement Learning. Transition Model Estimation. Dimensionality Reduction for Transition Model Estimation.
