000 01533cam a2200397La 4500
001 4248261
003 OSt
005 20170105113031.0
006 m u
007 cr cn-
008 000112s1998 maua sb 001 0 eng d
020 _a0585024456 (electronic bk.)
035 _a(OCoLC)43474535
035 _a(OCoLC)ocm43474535
035 _a(N$T)ocm43474535
035 _a(NNC)4248261
040 _aN$T
_cN$T
_dOCL
_dOCLCQ
050 1 4 _aQ325.6
_b.S88 1998eb
082 0 4 _a006.3/1
_221
100 1 _aSutton, Richard S.
245 1 0 _aReinforcement learning
_h[electronic resource] :
_ban introduction /
_cRichard S. Sutton and Andrew G. Barto.
260 _aCambridge, Mass. :
_bMIT Press,
_cc1998.
300 _axviii, 322 p. :
_bill. ;
_c24 cm.
490 1 _aAdaptive computation and machine learning
504 _aIncludes bibliographical references (p. [291]-312) and index.
533 _aElectronic reproduction.
_bBoulder, Colo. :
_cNetLibrary,
_d2000.
_nAvailable via the World Wide Web.
_nAvailable in multiple electronic file formats.
_nAccess may be limited to NetLibrary affiliated libraries.
650 0 _aReinforcement learning.
655 7 _aElectronic books.
_2local
700 1 _aBarto, Andrew G.
710 2 _aNetLibrary, Inc.
776 1 _cOriginal
_z0262193981
_w(DLC) 97026416
_w(OCoLC)37293240
830 0 _aAdaptive computation and machine learning.
856 4 _uhttp://www.columbia.edu/cgi-bin/cul/resolve?clio4248261
_zClick here for full text.
942 _2ddc
_cBK
999 _c31840
_d31840