Statements (31)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:algorithm
reinforcement learning method |
| gptkbp:application |
gptkb:Atari_games
video game playing |
| gptkbp:citation |
high
|
| gptkbp:component |
experience replay
target network |
| gptkbp:developedBy |
gptkb:DeepMind
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning deep learning |
| https://www.w3.org/2000/01/rdf-schema#label |
deep Q-network
|
| gptkbp:input |
raw pixels
|
| gptkbp:inspiredBy |
gptkb:Q-learning
|
| gptkbp:introducedIn |
2013
|
| gptkbp:notableContributor |
gptkb:Koray_Kavukcuoglu
gptkb:Volodymyr_Mnih gptkb:David_Silver gptkb:Demis_Hassabis |
| gptkbp:notablePublication |
gptkb:Playing_Atari_with_Deep_Reinforcement_Learning
|
| gptkbp:openSource |
gptkb:OpenAI_Baselines
gptkb:Stable_Baselines |
| gptkbp:output |
Q-values
|
| gptkbp:relatedTo |
gptkb:Q-learning
gptkb:reinforcement_learning deep reinforcement learning policy gradient methods |
| gptkbp:solvedBy |
reinforcement learning problems
|
| gptkbp:uses |
gptkb:model
|
| gptkbp:bfsParent |
gptkb:machine_learning
|
| gptkbp:bfsLayer |
4
|