Reinforcement Learning
Richard S. Sutton
2012-ж. дек. · The Springer International Series in Engineering and Computer Science 173-китеп · Springer Science & Business Media
5,0star
1 сын-пикирreport
Электрондук китеп
172
Барактар
reportРейтинг жана сын-пикирлер текшерилген жок Кеңири маалымат
Учкай маалымат
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.
Баалар жана сын-пикирлер
5,0
1 сын-пикир
Бул электрондук китепти баалаңыз
Оюңуз менен бөлүшүп коюңуз.
Окуу маалыматы
Смартфондор жана планшеттер
Android жана iPad/iPhone үчүн Google Play Китептер колдонмосун орнотуңуз. Ал автоматтык түрдө аккаунтуңуз менен шайкештелип, кайда болбоңуз, онлайнда же оффлайнда окуу мүмкүнчүлүгүн берет.
Ноутбуктар жана компьютерлер
Google Play'ден сатылып алынган аудиокитептерди компьютериңиздин веб браузеринен уга аласыз.
eReaders жана башка түзмөктөр
Kobo eReaders сыяктуу электрондук сыя түзмөктөрүнөн окуу үчүн, файлды жүктөп алып, аны түзмөгүңүзгө өткөрүшүңүз керек. Файлдарды колдоого алынган eReaders'ке өткөрүү үчүн Жардам борборунун нускамаларын аткарыңыз.
