Statements (13)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
reinforcement learning algorithm
|
| gptkbp:aimsTo |
reduce overestimation bias in Q-learning
|
| gptkbp:appliesTo |
deep reinforcement learning
|
| https://www.w3.org/2000/01/rdf-schema#label |
Double Q-learning
|
| gptkbp:introducedIn |
2010
|
| gptkbp:proposedBy |
gptkb:Hado_van_Hasselt
|
| gptkbp:publishedIn |
gptkb:AAAI_Conference_on_Artificial_Intelligence
|
| gptkbp:relatedTo |
gptkb:Q-learning
gptkb:Double_DQN |
| gptkbp:uses |
two value functions
|
| gptkbp:variant |
gptkb:Q-learning
|
| gptkbp:bfsParent |
gptkb:Double_DQN
|
| gptkbp:bfsLayer |
7
|