TY  - BOOK
AU  - Sutton, Richard S.
AU  - Barto, Andrew G.,
TI  - Reinforcement learning: an introduction 
T2  - Adaptive computation and machine learning series
SN  - 0262193981
U1  - 006.31 
PY  - 1998///
CY  - Cambridge, Mass.
PB  - MIT Press
KW  - Aprendizaje automático (Inteligencia artificial)
KW  - Aprendizaje por refuerzo
KW  - ARMARC 2.0 en línea
KW  - Inteligencia artificial
N1  - Includes bibliographical references  (p. [291]-312) and index; Evaluative Feedback -- The reinforcement learning problem -- Elementary solution methods -- Monte Carlo methods -- Temporal-Difference learning -- A unified view -- Generalization and function approximation -- Planning and learning
UR  - https://puce.odilo.us/info/reinforcement-learning-an-introduction-03335080
ER  -