Tallenna
Reinforcement Learning
nidottu, 2012
englanti
Reinforcement learning is the learning of a mapping from situations to actions so as to maximize a scalar reward or reinforcement signal. 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.
- Toimittaja
- Richard S. Sutton
- Painos
- Softcover reprint of the original 1st ed. 1992
- ISBN
- 9781461366089
- Kieli
- englanti
- Paino
- 310 grammaa
- Julkaisupäivä
- 8.10.2012
- Kustantaja
- Springer-Verlag New York Inc.
- Sivumäärä
- 172
