Описание: In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. This book provides an introduction to the RL transfer problem and discusses methods which demonstrate the promise of this exciting area of research.
Автор: Kofi Kissi Dompere Название: Fuzziness and Approximate Reasoning ISBN: 3642099890 ISBN-13(EAN): 9783642099892 Издательство: Springer Рейтинг: Цена: 19056 р. Наличие на складе: Поставка под заказ.
Описание: This text explains the epistemic structure of the relationships among uncertainty, expectations, risk, possibility and probability. It then probes how fuzzy paradigm and fuzzy rationality bring new understanding to those relationships.
Автор: Wiering Название: Reinforcement Learning ISBN: 364227644X ISBN-13(EAN): 9783642276446 Издательство: Springer Рейтинг: Цена: 32339 р. Наличие на складе: Поставка под заказ.
Описание: Reinforcement learning encompasses both a science of adaptive behavior of rational beings in uncertain environments and a computational methodology for finding optimal behaviors for challenging problems in control, optimization and adaptive behavior of intelligent agents. As a field, reinforcement learning has progressed tremendously in the past decade.The main goal of this book is to present an up-to-date series of survey articles on the main contemporary sub-fields of reinforcement learning. This includes surveys on partially observable environments, hierarchical task decompositions, relational knowledge representation and predictive state representations. Furthermore, topics such as transfer, evolutionary methods and continuous spaces in reinforcement learning are surveyed. In addition, several chapters review reinforcement learning methods in robotics, in games, and in computational neuroscience. In total seventeen different subfields are presented by mostly young experts in those areas, and together they truly represent a state-of-the-art of current reinforcement learning research.Marco Wiering works at the artificial intelligence department of the University of Groningen in the Netherlands. He has published extensively on various reinforcement learning topics. Martijn van Otterlo works in the cognitive artificial intelligence group at the Radboud University Nijmegen in The Netherlands. He has mainly focused on expressive knowledgerepresentation in reinforcement learning settings.
Описание: This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class of optimization problems. This synthesis is accomplished by customizing evolutionary methods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators. The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methods with manual representations.
Описание: Presenting the main results of new algorithms for reinforcement learning, this book also introduces a novel method for devising input representations as well as presenting a way to find a minimal set of features sufficient to describe the agent`s current state.
Описание: Reinforcement learning has evolved to tackle domains that are yet to be fully understood, or are too complex for a closed description. In this book the author investigates whether suitable abstraction methods can overcome the discipline`s deficiencies.
Описание: Reinforcement Learning Background.- Related Work.- Empirical Domains.- Value Function Transfer via Inter-Task Mappings.- Extending Transfer via Inter-Task Mappings.- Transfer between Different Reinforcement Learning Methods.- Learning Inter-Task Mappings.- Conclusion and Future Work.
Автор: Marco Wiering; Martijn van Otterlo Название: Reinforcement Learning ISBN: 364244685X ISBN-13(EAN): 9783642446856 Издательство: Springer Рейтинг: Цена: 26984 р. Наличие на складе: Поставка под заказ.
Описание: This book presents up-to-date information on the main contemporary sub-fields of reinforcement learning, including partially observable environments, hierarchical task decompositions, relational knowledge representation and predictive state representations.
Автор: Polkowski Название: Approximate Reasoning by Parts ISBN: 3642222781 ISBN-13(EAN): 9783642222788 Издательство: Springer Рейтинг: Цена: 24826 р. Наличие на складе: Поставка под заказ.
Описание: The monograph offers a view on Rough Mereology, a tool for reasoning under uncertainty, which goes back to Mereology, formulated in terms of parts by Lesniewski, and borrows from Fuzzy Set Theory and Rough Set Theory ideas of the containment to a degree. The result is a theory based on the notion of a part to a degree. One can invoke here a formula Rough: Rough Mereology : Mereology = Fuzzy Set Theory : Set Theory. As with Mereology, Rough Mereology finds important applications in problems of Spatial Reasoning, illustrated in this monograph with examples from Behavioral Robotics. Due to its involvement with concepts, Rough Mereology offers new approaches to Granular Computing, Classifier and Decision Synthesis, Logics for Information Systems, and are--formulation of well--known ideas of Neural Networks and Many Agent Systems. All these approaches are discussed in this monograph. To make the exposition self--contained, underlying notions of Set Theory, Topology, and Deductive and Reductive Reasoning with emphasis on Rough and Fuzzy Set Theories along with a thorough exposition of Mereology both in Lesniewski and Whitehead--Leonard--Goodman--Clarke versions are discussed at length. It is hoped that the monograph offers researchers in various areas of Artificial Intelligence a new tool to deal with analysis of relations among concepts.
Автор: Eyke H?llermeier Название: Case-Based Approximate Reasoning ISBN: 9048174317 ISBN-13(EAN): 9789048174317 Издательство: Springer Рейтинг: Цена: 19056 р. Наличие на складе: Поставка под заказ.
Описание: Making use of different frameworks of approximate reasoning and reasoning under uncertainty, notably probabilistic and fuzzy set-based techniques, this book develops formal models of the above inference principle, which is fundamental to CBR.
Описание: The central idea of Hebbian Learning and Negative Feedback Networks is that artificial neural networks using negative feedback of activation can use simple Hebbian learning to self-organise so that they uncover interesting structures in data sets. Two variants are considered: the first uses a single stream of data to self-organise. By changing the learning rules for the network, it is shown how to perform Principal Component Analysis, Exploratory Projection Pursuit, Independent Component Analysis, Factor Analysis and a variety of topology preserving mappings for such data sets. The book encompasses a wide range of real experiments and displays how the approaches it formulates can be applied to the analysis of real problems.
Описание: This book presents the framework for the versatile specification of physical interaction tasks, as well as the problem of autonomous planning of these tasks. It details novel grasp-task sensor-based control methods using vision, tactile and force feedback.
ООО "Логосфера " Тел:+7(495) 980-12-10 www.logobook.ru