{"product_id":"9780792397458","title":"The Springer International Series in Engineering and Computer Science: Machine Learning","description":"\u003ch1\u003eThe Springer International Series in Engineering and Computer Science: Machine Learning\u003c\/h1\u003e \u003ch2\u003eFranklin, Judy A.; Mitchell, Tom M.; Thrun, Sebastian\u003c\/h2\u003e \u003cp\u003e\u003cem\u003eRecent Advances in Robot Learning\u003c\/em\u003e contains seven papers  on robot learning written by leading researchers in the field. As the  selection of papers illustrates, the field of robot learning is both  active and diverse. A variety of machine learning methods, ranging  from inductive logic programming to reinforcement learning, is being  applied to many subproblems in robot perception and control, often  with objectives as diverse as parameter calibration and concept  formulation. \u003cbr\u003e  While no unified robot learning framework has yet emerged to cover the  variety of problems and approaches described in these papers and other  publications, a clear set of shared issues underlies many robot  learning problems. \u003cbr\u003e  \u003c\/p\u003e\u003cul\u003e \u003cli\u003eMachine learning, when applied to robotics, is  situated: it is embedded into a real-world system that tightly  integrates perception, decision making and execution. \u003c\/li\u003e  \u003cli\u003eSince  robot learning involves decision making, there is an inherent active  learning issue. \u003c\/li\u003e  \u003cli\u003eRobotic domains are usually complex, yet the  expense of using actual robotic hardware often prohibits the  collection of large amounts of training data. \u003c\/li\u003e  \u003cli\u003eMost robotic  systems are real-time systems. Decisions must be made within critical  or practical time constraints. \u003c\/li\u003e  \u003c\/ul\u003e  \u003cbr\u003e  These characteristics present challenges and constraints to the  learning system. Since these characteristics are shared by other  important real-world application domains, robotics is a highly  attractive area for research on machine learning. \u003cbr\u003e  On the other hand, machine learning is also highly attractive to  robotics. There is a great variety of open problems in robotics that  defy a static, hand-coded solution. \u003cbr\u003e  \u003cem\u003eRecent Advances in Robot Learning\u003c\/em\u003e is an edited volume of  peer-reviewed original research comprising seven invited contributions  by leading researchers. This research work has also been published as  a special issue of \u003cem\u003eMachine Learning\u003c\/em\u003e (Volume 23, Numbers 2 and  3). \u003ch3\u003eDetails\u003c\/h3\u003e \u003cp\u003ePublished by: Springer\u003c\/p\u003e \u003cp\u003ePublication Date: 1996-06-30\u003c\/p\u003e \u003cp\u003eFormat: Hardcover\u003c\/p\u003e \u003cp\u003eISBN-13: 9780792397458\u003c\/p\u003e \u003cp\u003eDOI: 10.1007\/978-1-4613-0471-5\u003c\/p\u003e \u003cp\u003eDimensions: 235cm x155cm\u003c\/p\u003e \u003cp\u003ePages: 218\u003c\/p\u003e ","brand":"Springer US","offers":[{"title":"Default Title","offer_id":44343363436684,"sku":"9780792397458","price":152.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0710\/9545\/1788\/files\/9780792397458.jpg?v=1771511154","url":"https:\/\/lateknightbooks.com\/products\/9780792397458","provider":"Late Knight Books and Services, LLC","version":"1.0","type":"link"}