|
Titre :
|
Neuro-dynamic programming
|
|
Auteurs :
|
D. Bertsekas ;
J. Tsitsiklis
|
|
Type de document :
|
ouvrage
|
|
Editeur :
|
Belmont, USA : Athena scientific, 1996
|
|
Format :
|
491 p.
|
|
Langues :
|
= Anglais
|
|
Catégories :
|
INTELLIGENCE ARTIFICIELLE
|
|
Mots-clés :
|
RESEAU DE NEURONES
;
ALGORITHME
;
RENFORCEMENT
;
APPRENTISSAGE
;
SIMULATION
|
|
Résumé :
|
Neuro-dynamic programming, also known as reinforcement learning is a recent methodology that can be used to solve very large and complex stochastic decision and control problems. It combines simulation, learning, neural networks or other approximation architectures, and the central ideas in dynamic programming. This book provides the first systematic presentation of the science and the art behind this promising methodology.
|
