TY  - BOOK
AU  - Sutton,Richard S.
AU  - Barto,Andrew G.
TI  - Reinforcement learning: : an introduction
T2  - Adaptive computation and machine learning
PY  - 2018///]
CY  - Cambridge, Massachusetts
PB  - MIT Press
KW  - Reinforcement learning
KW  - Electronic Books
N1  - Includes bibliographical references and index; Reinforcement learning; Part I. Tabular solution methods; Multi-armed bandits; Finite Markov decision processes; Dynamic programming; Monte Carlo methods; Temporal-difference learning; n-step bootstrapping; Planning and learning with tabular methods; Part II. Approximate solution methods; On-policy prediction with approximation; On-policy control with approximation; Off-policy methods with approximation; Eligibility traces; Policy gradient methods; Part III. Looking deeper; Psychology; Neuroscience; Applications and case studies; Frontiers
UR  - https://www.andrew.cmu.edu/course/10-703/textbook/BartoSutton.pdf
ER  -