Maria Domenica Di Benedetto – författare

Model-Based Reinforcement Learning Explore a comprehensive and practical approach to reinforcement learning Reinforcement learning is an essential paradigm of machine learning, wherein an intelligent agent performs actions that ensure optimal behavior from devices. While this paradigm of machine learning has gained tremendous success and popularity in recent years, previous scholarship has focused either on theory—optimal control and dynamic programming – or on algorithms—most of which are simulation-based. Model-Based Reinforcement Learning provides a model-based framework to bridge these two aspects, thereby creating a holistic treatment of the topic of model-based online learning control. In doing so, the authors seek to develop a model-based framework for data-driven control that bridges the topics of systems identification from data, model-based reinforcement learning, and optimal control, as well as the applications of each. This new technique for assessing classical results will allow for a more efficient reinforcement learning system. At its heart, this book is focused on providing an end-to-end framework—from design to application—of a more tractable model-based reinforcement learning technique. Model-Based Reinforcement Learning readers will also find: A useful textbook to use in graduate courses on data-driven and learning-based control that emphasizes modeling and control of dynamical systems from dataDetailed comparisons of the impact of different techniques, such as basic linear quadratic controller, learning-based model predictive control, model-free reinforcement learning, and structured online learningApplications and case studies on ground vehicles with nonholonomic dynamics and another on quadrator helicoptersAn online, Python-based toolbox that accompanies the contents covered in the book, as well as the necessary code and dataModel-Based Reinforcement Learning is a useful reference for senior undergraduate students, graduate students, research assistants, professors, process control engineers, and roboticists.

This book focuses on the observability of hybrid systems. It enables the reader to determine whether and how a hybrid system’s state can be reconstructed from sometimes necessarily partial information. By explaining how available measurements can be used to deduce past and future behaviours of a system, the authors extend this study of observability to embrace the properties of diagnosability and predictability.H-systems shows how continuous and discrete dynamics and their interaction affect the observability of this general class of hybrid systems and demonstrates that hybrid characteristics are not simply generalizations of well-known aspects of traditional dynamics. The authors identify conditions for state reconstruction, prediction and diagnosis of the occurrence of possibly faulty states. The formal approach to proving those properties for hybrid systems is accompanied by simple illustrative examples. For readers who are interested in the use of state estimation for controller design, the book also provides design methods for hybrid state observers and covers their application in some industrial cases.The book’s tutorial approach to the various forms of observability of hybrid systems helps to make H-systems of interest to academic researchers and graduate students working in control and to practitioners using control in an industrial environment.

This book focuses on the observability of hybrid systems. It enables the reader to determine whether and how a hybrid system’s state can be reconstructed from sometimes necessarily partial information. By explaining how available measurements can be used to deduce past and future behaviours of a system, the authors extend this study of observability to embrace the properties of diagnosability and predictability.H-systems shows how continuous and discrete dynamics and their interaction affect the observability of this general class of hybrid systems and demonstrates that hybrid characteristics are not simply generalizations of well-known aspects of traditional dynamics. The authors identify conditions for state reconstruction, prediction and diagnosis of the occurrence of possibly faulty states. The formal approach to proving those properties for hybrid systems is accompanied by simple illustrative examples. For readers who are interested in the use of state estimation for controller design, the book also provides design methods for hybrid state observers and covers their application in some industrial cases.The book’s tutorial approach to the various forms of observability of hybrid systems helps to make H-systems of interest to academic researchers and graduate students working in control and to practitioners using control in an industrial environment.