Statements (25)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
reinforcement learning algorithm
|
| gptkbp:address |
overestimation bias in Q-learning
|
| gptkbp:application |
gptkb:reinforcement_learning
deep learning |
| gptkbp:category |
gptkb:artificial_intelligence
gptkb:machine_learning |
| gptkbp:citation |
high
|
| gptkbp:fullName |
Double Deep Q-Network
|
| https://www.w3.org/2000/01/rdf-schema#label |
Double DQN
|
| gptkbp:improves |
gptkb:DQN
|
| gptkbp:notablePaperTitle |
gptkb:Deep_Reinforcement_Learning_with_Double_Q-learning
|
| gptkbp:notablePaperURL |
https://arxiv.org/abs/1509.06461
|
| gptkbp:proposedBy |
gptkb:David_Silver
gptkb:Arthur_Guez gptkb:Hado_van_Hasselt |
| gptkbp:publicationYear |
2016
|
| gptkbp:publishedIn |
gptkb:AAAI_Conference_on_Artificial_Intelligence
|
| gptkbp:relatedTo |
gptkb:Q-learning
gptkb:Deep_Q-Network_(DQN) gptkb:Double_Q-learning |
| gptkbp:usedIn |
Atari 2600 benchmark
|
| gptkbp:uses |
two value networks
|
| gptkbp:bfsParent |
gptkb:Deep_Q-Network
gptkb:Deep_Q-Network_(DQN) |
| gptkbp:bfsLayer |
6
|