Human-level control through deep reinforcement learning

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:academic_journal
gptkbp:affiliation	gptkb:DeepMind
gptkbp:author	gptkb:Koray_Kavukcuoglu gptkb:Volodymyr_Mnih gptkb:Ioannis_Antonoglou gptkb:Martin_Riedmiller gptkb:David_Silver gptkb:Demis_Hassabis gptkb:Shane_Legg gptkb:Alex_Graves gptkb:Helen_King gptkb:Daan_Wierstra gptkb:Andreas_K._Fidjeland gptkb:Andrei_A._Rusu gptkb:Charles_Beattie gptkb:Dharshan_Kumaran gptkb:Georg_Ostrovski gptkb:Joel_Veness gptkb:Marc_G._Bellemare gptkb:Stig_Petersen Amir Sadik
gptkbp:citation	thousands of scientific papers
gptkbp:contribution	introduction of deep Q-network (DQN) demonstration of human-level performance on Atari 2600 games
gptkbp:doi	10.1038/nature14236
gptkbp:field	gptkb:artificial_intelligence gptkb:reinforcement_learning deep learning
https://www.w3.org/2000/01/rdf-schema#label	Human-level control through deep reinforcement learning
gptkbp:pages	529-533
gptkbp:publicationDate	2015
gptkbp:publishedIn	gptkb:Nature
gptkbp:publisher	gptkb:Nature_Publishing_Group
gptkbp:volume	518
gptkbp:bfsParent	gptkb:Volodymyr_Mnih
gptkbp:bfsLayer	6