000 01214nam a22003017a 4500
005 20250922143652.0
008 250922b |||||||| |||| 00| 0 eng d
020 _a978-0-262-19398-6
040 _cSYAMALA BOOK LINKS
041 _aENGLISH
082 _a006.31 SUT
100 _aSUTTON S RICHARD
245 _aREINFORCEMENT LEARNING
_bAN INTRODUCTION
250 _aSECOND EDITION
260 _aLONDON
_bTHE MIT PRESS
_c2018
300 _aXIX 526P
365 _b6450
_c
500 _aOPTIMIZATION & AUTOMATION
520 _a"Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto is a fundamental textbook detailing how an agent learns optimal decisions by interacting with an environment to maximize a reward signal. The book covers core concepts such as agents, environments, policies, reward signals, and value functions, and explores methods like Dynamic Programming, Monte Carlo, and Temporal-Difference learning.
522 _aComputer Science
526 _aALL ENGINEERING BRANCHES
650 _aCOMPUTER SCIENCE
651 _aENGINEERING
658 _cR23
700 _aBARTO G ANDREW
760 _bSECOND EDITION
942 _2ddc
_cREF
_eSECOND EDITION
_n0
999 _c18321
_d18321