00355nam a2200157Ia 450000500170000000800410001702000180005803500080007608200140008410000170009824500440011525000060015926000140016530000080017950000100018720260507132856.0260506s9999||||xx |||||||||||||| ||und||  a9780262039246  a756  a6.31BFRA  aFrancis Bach 0aReinforcement Learning: An Introduction  a2  bMITc2018  a526  a16527