000			01581cam a2200337 i 4500
999			_c3 _d3
001			20515853
003			OSt
005			20191021125743.0
008			180525s2018 maua b 001 0 eng
010			_a 2018023826
020			_a9780262039246 (hardcover : alk. paper)
040			_aDLC _beng _cKCST _erda _eDLC _dDLC
042			_apcc
050	0	0	_aQ325.6 _b.R45 2018
082	0	0	_a006.3/1 _223
100	1		_aSutton, Richard S., _eauthor. _944
245	1	0	_aReinforcement learning : _ban introduction / _cRichard S. Sutton and Andrew G. Barto.
250			_aSecond edition.
260			_aCambridge, Massachusetts : _bThe MIT Press, _c[2018]
264		1	_aCambridge, Massachusetts : _bThe MIT Press, _c[2018]
300			_axxii, 526 pages : _billustrations (some color) ; _c24 cm.
336			_atext _btxt _2rdacontent
337			_aunmediated _bn _2rdamedia
338			_avolume _bnc _2rdacarrier
490	0		_aAdaptive computation and machine learning series
504			_aIncludes bibliographical references (pages 481-518) and index.
520			_a"Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms."-- _cProvided by publisher.
650		0	_aReinforcement learning. _945
700	1		_aBarto, Andrew G., _eauthor. _946
942			_2ddc _cBO