LEADER 01490nam  2200397   450 
001 9910713758203321
005 20200730153553.0
035   $a(CKB)5470000002504101
035   $a(OCoLC)1179160559
035   $a(EXLCZ)995470000002504101
100   $a20200730d2019      ua             0
101 0 $aeng
135   $aur|||||||||||
181   $ctxt$2rdacontent
182   $cc$2rdamedia
183   $acr$2rdacarrier
200 10$aQuasi-stochastic approximation and off-policy reinforcement learning $epreprint /$fAndrey Bernstein [and five others]
210  1$aGolden, CO :$cNational Renewable Energy Laboratory,$d2019.
215   $a1 online resource (8 pages) $ccolor illustrations
225 1 $aNREL/CP ;$v5D00-73518
300   $a"Presented at the 2019 IEEE Conference on Decision and Control (IEEE CDC), Nice, France, December 11-13, 2019."
300   $a"December 2019."
320   $aIncludes bibliographical references (page 8).
517   $aQuasi-stochastic approximation and off-policy reinforcement learning 
606   $aReinforcement learning
606   $aStochastic approximation
615  0$aReinforcement learning.
615  0$aStochastic approximation.
700   $aBernstein$b Andrey$01401176
712 02$aNational Renewable Energy Laboratory (U.S.),
801  0$bGPO
801  1$bGPO
906   $aBOOK
912   $a9910713758203321
996   $aQuasi-stochastic approximation and off-policy reinforcement learning$93469533
997   $aUNINA