000			01781nam a2200241Ia 4500
003			NULRC
005			20250520103029.0
008			250520s9999 xx 000 0 und d
020			_a9798845864970
040			_cNULRC
050			_aQ 325.6 .S88 2018
100			_aSutton, Richard S. _eauthor
245		0	_aReinforcement learning : _ban introduction / _cRichard S. Sutton and Andrew G. Barto
250			_aSecond Edition.
260			_aCambridge, Massachusetts : _bThe MIT Press, _cc2018
300			_axviii, 524 pages : _billustrations ; _c24 cm.
365			_bUSD27
504			_aIncludes bibliographical references and index.
505			_aSummary of Notation -- I. Tabular Solution Methods -- II. Approximate Solution Methods -- III. Looking Deeper -- References -- Index.
520			_aThis second edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new to the second edition, including UCB, Expected Sarsa, and Double Learning. Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods. Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.
650			_aREINFORCEMENT LEARNING
942			_2lcc _cBK
999			_c21788 _d21788