Statements (30)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:algorithm
reinforcement learning algorithm |
| gptkbp:abbreviation |
gptkb:DQN
|
| gptkbp:appliesTo |
gptkb:Atari_2600_games
|
| gptkbp:citation |
gptkb:Mnih_et_al.,_2015
|
| gptkbp:developedBy |
gptkb:DeepMind
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning gptkb:reinforcement_learning deep learning |
| https://www.w3.org/2000/01/rdf-schema#label |
Deep Q-Network
|
| gptkbp:influenced |
gptkb:Double_DQN
gptkb:Dueling_DQN gptkb:Rainbow_DQN |
| gptkbp:input |
image frames
|
| gptkbp:introducedIn |
2013
|
| gptkbp:language |
gptkb:Python
|
| gptkbp:notableFor |
learning to play video games from raw pixels
|
| gptkbp:output |
Q-values
|
| gptkbp:platform |
gptkb:TensorFlow
gptkb:PyTorch |
| gptkbp:publishedIn |
gptkb:Nature
|
| gptkbp:solvedBy |
gptkb:Markov_Decision_Process
|
| gptkbp:uses |
gptkb:model
gptkb:Q-learning experience replay target network epsilon-greedy policy |
| gptkbp:bfsParent |
gptkb:Q-learning
|
| gptkbp:bfsLayer |
5
|