Reinforcement learning explained
Auteur :
Rizk, Rodrigue / Baride, Srikanth / Santosh, KC
Éditeur :
Taylor & Francis Ltd
ISBN :
9781041252993
Date de publication :
15 mars 2027
Dimensions :
23,4 x 15,6 cm
Langue :
Anglais
Pays d'origine :
Grande Bretagne
This book provides a rigorous yet accessible foundation in reinforcement learning, covering mathematical principles and practical methods. It introduces MDPs, value functions, Bellman equations, and classical solution methods including dynamic programming, Monte Carlo, and Q-learning, with Python implementations.