Dueling Network Architectures for Deep Reinforcement Learning
GPTKB entity
Statements (24)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:academic_journal
|
gptkbp:application |
gptkb:Atari_2600_games
|
gptkbp:arXivID |
1511.06581
|
gptkbp:author |
gptkb:Nando_de_Freitas
gptkb:Hado_van_Hasselt gptkb:Marc_Lanctot gptkb:Matteo_Hessel gptkb:Tom_Schaul gptkb:Ziyu_Wang |
gptkbp:citation |
high
|
gptkbp:contribution |
separates value and advantage streams in Q-networks
|
gptkbp:field |
gptkb:artificial_intelligence
deep reinforcement learning |
gptkbp:focusesOn |
gptkb:Q-learning
|
gptkbp:hasMethod |
dueling network architecture
|
https://www.w3.org/2000/01/rdf-schema#label |
Dueling Network Architectures for Deep Reinforcement Learning
|
gptkbp:influenced |
deep Q-networks
|
gptkbp:organization |
gptkb:DeepMind
|
gptkbp:publicationYear |
2016
|
gptkbp:publishedIn |
gptkb:International_Conference_on_Machine_Learning
|
gptkbp:url |
https://arxiv.org/abs/1511.06581
|
gptkbp:bfsParent |
gptkb:International_Conference_on_Machine_Learning_2016
gptkb:Dueling_DQN |
gptkbp:bfsLayer |
7
|