000			00387nam a2200169Ia 4500
008			260109s9999||||xx |||||||||||||| ||und||
020			_a9780262039246
035			_a111
082			_a006.3 _BSUT
100			_aSutton, Richard S.; Barto, Andrew G.
245		0	_aReinforcement Learning
250			_a2
260			_bMIT Press _c2018
300			_a526
500			_a1780
942			_cBK
999			_c27055 _d27055