000			00521nam a22001937a 4500
005			20220518154816.0
008			190201b xxu||||| |||| 00| 0 eng d
020			_a9780262039246
041			_aeng
082			_a004.85 _bSUT
100			_aSutton, Richard S _93240
245			_aReinforcement learning _b:an introduction
250			_a2nd ed.
260			_aCambridge _bMIT _c2018
300			_a526p.
650			_areinforcement--learning _alearning--reinforcement _93241
700			_aBarto, Andrew G _93242
942			_cBK
999			_c241833 _d241833