LEADER 00499nam  2200193zu 450 
001 9910918090003321
005 20241203191033.0
035   $a(CKB)36718693300041
035   $a(EXLCZ)9936718693300041
100   $a20241203|2023uuuu  ||         |
101 0 $aeng
135   $aur|||||||||||
200 10$aCivil Society Elites
210   $cNIAS Press$d2023
700   $aNorén-Nilsson$b Astrid$01742188
906   $aBOOK
912   $a9910918090003321
996   $aCivil Society Elites$94305641
997   $aUNINA

LEADER 01731nam  2200373z- 450 
001 9910346911203321
005 20210211
010   $a1-000-01979-9
035   $a(CKB)4920000000101410
035   $a(oapen)https://directory.doabooks.org/handle/20.500.12854/45907
035   $a(oapen)doab45907
035   $a(EXLCZ)994920000000101410
100   $a20202102d2010      |y         0
101 0 $aeng
135   $aurmn|---annan
181   $ctxt$2rdacontent
182   $cc$2rdamedia
183   $acr$2rdacarrier
200 00$aEfficient Reinforcement Learning using Gaussian Processes
210   $cKIT Scientific Publishing$d2010
215   $a1 online resource (IX, 205 p. p.)
225 1 $aKarlsruhe Series on Intelligent Sensor-Actuator-Systems / Karlsruher Institut für Technologie, Intelligent Sensor-Actuator-Systems Laboratory
311 08$a3-86644-569-5 
330   $aThis book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model uncertainties consistently into account during long-term planning to reduce model bias. Second, we propose principled algorithms for robust filtering and smoothing in GP dynamic systems.
610   $aautonomous learning
610   $aBayesian inference
610   $acontrol
610   $aGaussian processes
610   $amachine learning
700   $aDeisenroth$b Marc Peter$4auth$01295433
906   $aBOOK
912   $a9910346911203321
996   $aEfficient Reinforcement Learning using Gaussian Processes$93023440
997   $aUNINA