Bemærk: Kan ikke leveres før jul.
Forventes på lager: 26-09-2014
The book begins with a chapter on traditional methods of supervised learning, covering recursive least squares learning, mean square error methods, and stochastic approximation. Chapter 2 covers single agent reinforcement learning. Topics include learning value functions, Markov games, and TD learning with eligibility traces.
| Forlag | John Wiley & Sons Inc |
| Forfatter | H. M. Schwartz |
| Type | Bog |
| Format | Hardback |
| Sprog | Engelsk |
| Udgivelsesdato | 26-09-2014 |
| Første udgivelsesår | 2014 |
| Originalsprog | United States |
| Sideantal | 256 |
| Indbinding | Hardback |
| Forlag | John Wiley & Sons Inc |
| Sideoplysninger | 256 pages |
| Mål | 163 x 238 x 18 |
| ISBN-13 / EAN-13 | 9781118362082 |