Reinforcement Learning
Richard S. Sutton
ديسمبر 2012 · The Springer International Series in Engineering and Computer Science الكتاب 173 · Springer Science & Business Media
5.0star
مراجعة واحدةreport
كتاب إلكتروني
172
صفحة
reportلم يتم التحقّق من التقييمات والمراجعات. مزيد من المعلومات
معلومات عن هذا الكتاب الإلكتروني
Reinforcement learning is the learning of a mapping from situations to actions so as to maximize a scalar reward or reinforcement signal. The learner is not told which action to take, as in most forms of machine learning, but instead must discover which actions yield the highest reward by trying them. In the most interesting and challenging cases, actions may affect not only the immediate reward, but also the next situation, and through that all subsequent rewards. These two characteristics -- trial-and-error search and delayed reward -- are the most important distinguishing features of reinforcement learning.
Reinforcement learning is both a new and a very old topic in AI. The term appears to have been coined by Minsk (1961), and independently in control theory by Walz and Fu (1965). The earliest machine learning research now viewed as directly relevant was Samuel's (1959) checker player, which used temporal-difference learning to manage delayed reward much as it is used today. Of course learning and reinforcement have been studied in psychology for almost a century, and that work has had a very strong impact on the AI/engineering work. One could in fact consider all of reinforcement learning to be simply the reverse engineering of certain psychological learning processes (e.g. operant conditioning and secondary reinforcement).
Reinforcement Learning is an edited volume of original research, comprising seven invited contributions by leading researchers.
Reinforcement learning is both a new and a very old topic in AI. The term appears to have been coined by Minsk (1961), and independently in control theory by Walz and Fu (1965). The earliest machine learning research now viewed as directly relevant was Samuel's (1959) checker player, which used temporal-difference learning to manage delayed reward much as it is used today. Of course learning and reinforcement have been studied in psychology for almost a century, and that work has had a very strong impact on the AI/engineering work. One could in fact consider all of reinforcement learning to be simply the reverse engineering of certain psychological learning processes (e.g. operant conditioning and secondary reinforcement).
Reinforcement Learning is an edited volume of original research, comprising seven invited contributions by leading researchers.
التقييمات والتعليقات
5.0
مراجعة واحدة
تقييم هذا الكتاب الإلكتروني
أخبرنا ما هو رأيك.
معلومات القراءة
الهواتف الذكية والأجهزة اللوحية
ينبغي تثبيت تطبيق كتب Google Play لنظام التشغيل Android وiPad/iPhone. يعمل هذا التطبيق على إجراء مزامنة تلقائية مع حسابك ويتيح لك القراءة أثناء الاتصال بالإنترنت أو بلا اتصال بالإنترنت أينما كنت.
أجهزة الكمبيوتر المحمول وأجهزة الكمبيوتر
يمكنك الاستماع إلى الكتب المسموعة التي تم شراؤها على Google Play باستخدام متصفح الويب على جهاز الكمبيوتر.
أجهزة القراءة الإلكترونية والأجهزة الأخرى
للقراءة على أجهزة الحبر الإلكتروني، مثل أجهزة القارئ الإلكتروني Kobo، عليك تنزيل ملف ونقله إلى جهازك. يُرجى اتّباع التعليمات المفصّلة في مركز المساعدة لتتمكّن من نقل الملفات إلى أجهزة القارئ الإلكتروني المتوافقة.
