Reinforcement Learning (häftad)
Häftad (Paperback / softback)
Antal sidor
Softcover reprint of the original 1st ed. 1992
Springer-Verlag New York Inc.
Sutton, Richard S. (ed.)
172 p.
234 x 156 x 10 mm
259 g
Antal komponenter
1 Paperback / softback
Reinforcement Learning (häftad)

Reinforcement Learning

Häftad Engelska, 2012-10-08
  • Skickas inom 7-10 vardagar.
  • Gratis frakt inom Sverige över 159 kr för privatpersoner.
Kan levereras innan julafton!
Finns även som
Visa alla 6 format & utgåvor
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.
Visa hela texten

Passar bra ihop

  1. Reinforcement Learning
  2. +
  3. This Is How They Tell Me the World Ends

De som köpt den här boken har ofta också köpt This Is How They Tell Me the World Ends av Nicole Perlroth (häftad).

Köp båda 2 för 2338 kr


Har du läst boken? Sätt ditt betyg »

Fler böcker av Richard S Sutton

  • Neural Networks for Control

    W Thomas Miller Iii, Richard S Sutton, Paul J Werbos

    Neural Networks for Control highlights key issues in learning control and identifies research directions that could lead to practical solutions for control problems in critical application domains. It addresses general issues of neural network bas...


Introduction; R.Sutton. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning; R.J. Wiiliams. Practical Issues in Temporal Difference Learning; G. Teasauro. Technical Note: Q-Learning; C.J.C.H. Watkins, P. Dayan. Self Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching; L.-J. Lin. Transfer of Learning by Composing Solutions of Elemental Sequential Tasks; S.P. Singh. The Convergence of TD (lambda) for general lambda; P. Dayan. A Reinforcement Connctionist Approach to Robot Path Finding in Non-Maze-Like Environments; J. del R. Millan, C. Torras.