Deep Reinforcement Learning with Double Q-learning
GPTKB entity
Statements (20)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic_journal
|
gptkbp:affiliation |
gptkb:DeepMind
|
gptkbp:application |
gptkb:Atari_2600_games
|
gptkbp:author |
gptkb:David_Silver
gptkb:Arthur_Guez gptkb:Hado_van_Hasselt |
gptkbp:citation |
gptkb:Deep_Q-Network_(DQN)
|
gptkbp:contribution |
Introduced Double DQN to reduce overestimation bias in Q-learning
|
gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning gptkb:reinforcement_learning |
gptkbp:hasMethod |
gptkb:Double_DQN
|
https://www.w3.org/2000/01/rdf-schema#label |
Deep Reinforcement Learning with Double Q-learning
|
gptkbp:impact |
Widely cited in reinforcement learning research
|
gptkbp:improves |
gptkb:DQN
|
gptkbp:publicationYear |
2016
|
gptkbp:publishedIn |
gptkb:AAAI_Conference_on_Artificial_Intelligence
|
gptkbp:url |
https://arxiv.org/abs/1509.06461
|
gptkbp:bfsParent |
gptkb:Double_DQN
|
gptkbp:bfsLayer |
7
|