Transfer in Reinforcement Learning Domains, Matthew Taylor

Автор: Matthew Taylor
Название: Transfer in Reinforcement Learning Domains
ISBN: 3642018815 ISBN-13(EAN): 9783642018817
Издательство: Springer
Рейтинг:
Цена: 23757.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

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: Lutz Frommberger
Название: Qualitative Spatial Abstraction in Reinforcement Learning
ISBN: 3642266002 ISBN-13(EAN): 9783642266003
Издательство: Springer
Рейтинг:
Цена: 16070.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

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.

Автор: Larbani
Название: Wonderful Solutions and Habitual Domains for Challenging Problems in Changeable Spaces
ISBN: 9811019797 ISBN-13(EAN): 9789811019791
Издательство: Springer
Рейтинг:
Цена: 19564.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание: This book introduces a new paradigm called ‘Optimization in Changeable Spaces’ (OCS) as a useful tool for decision making and problem solving. It illustrates how OCS incorporates, searches, and constructively restructures the parameters, tangible and intangible, involved in the process of decision making. The book elaborates on OCS problems that can be modeled and solved effectively by using the concepts of competence set analysis, Habitual Domain (HD) and the mental operators called the 7-8-9 principles of deep knowledge of HD. In addition, new concepts of covering and discovering processes are proposed and formulated as mathematical tools to solve OCS problems. The book also includes reformulations of a number of illustrative real-life challenging problems that cannot be solved by traditional optimization techniques into OCS problems, and details how they can be addressed. Beyond that, it also includes perspectives related to innovation dynamics, management, artificial intelligence, artificial and e-economics, scientific discovery and knowledge extraction. This book will be of interest to managers of businesses and institutions, policy makers, and educators and students of decision making and behavior in DBA and/or MBA.

Автор: Marco Wiering; Martijn van Otterlo
Название: Reinforcement Learning
ISBN: 364244685X ISBN-13(EAN): 9783642446856
Издательство: Springer
Рейтинг:
Цена: 32651.00 р.
Наличие на складе: Есть у поставщика 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: Shimon Whiteson
Название: Adaptive Representations for Reinforcement Learning
ISBN: 3642422314 ISBN-13(EAN): 9783642422317
Издательство: Springer
Рейтинг:
Цена: 15672.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

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.