.png){kind=logo}
Stock image for illustration purposes only - book cover, edition or condition may vary.
Adaptive Representations for Reinforcement Learning
Shimon Whiteson
€ 127.40
FREE Delivery in Ireland
Description for Adaptive Representations for Reinforcement Learning
Hardback. 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. Series: Studies in Computational Intelligence. Num Pages: 116 pages, biography. BIC Classification: TBC; UYQ. Category: (P) Professional & Vocational. Dimension: 235 x 155 x 13. Weight in Grams: 392.
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 ... Read more
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 ... Read more
Product Details
Format
Hardback
Publication date
2010
Publisher
Springer-Verlag Berlin and Heidelberg GmbH & Co. KG Germany
Number of pages
116
Condition
New
Series
Studies in Computational Intelligence
Number of Pages
116
Place of Publication
Berlin, Germany
ISBN
9783642139314
SKU
V9783642139314
Shipping Time
Usually ships in 15 to 20 working days
Ref
99-15
Reviews for Adaptive Representations for Reinforcement Learning