Reinforcement Learning
Richard S. Sutton
Δεκ 2012 · The Springer International Series in Engineering and Computer Science Βιβλίο 173 · Springer Science & Business Media
5,0star
1 κριτικήreport
ebook
172
Σελίδες
reportΟι αξιολογήσεις και οι κριτικές δεν επαληθεύονται Μάθετε περισσότερα
Σχετικά με το ebook
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.
Βαθμολογίες και αξιολογήσεις
5,0
1 αξιολόγηση
Αξιολογήστε αυτό το ebook
Πείτε μας τη γνώμη σας.
Πληροφορίες ανάγνωσης
Smartphone και tablet
Εγκαταστήστε την εφαρμογή Βιβλία Google Play για Android και iPad/iPhone. Συγχρονίζεται αυτόματα με τον λογαριασμό σας και σας επιτρέπει να διαβάζετε στο διαδίκτυο ή εκτός σύνδεσης, όπου κι αν βρίσκεστε.
Φορητοί και επιτραπέζιοι υπολογιστές
Μπορείτε να ακούσετε ηχητικά βιβλία τα οποία αγοράσατε στο Google Play, χρησιμοποιώντας το πρόγραμμα περιήγησης στον ιστό του υπολογιστή σας.
eReader και άλλες συσκευές
Για να διαβάσετε περιεχόμενο σε συσκευές e-ink, όπως είναι οι συσκευές Kobo eReader, θα χρειαστεί να κατεβάσετε ένα αρχείο και να το μεταφέρετε στη συσκευή σας. Ακολουθήστε τις αναλυτικές οδηγίες του Κέντρου βοήθειας για να μεταφέρετε αρχεία σε υποστηριζόμενα eReader.
