|
gptkbp:instanceOf
|
deep reinforcement learning algorithm
|
|
gptkbp:appliesTo
|
gptkb:Atari_2600_games
|
|
gptkbp:arXivID
|
1710.02298
|
|
gptkbp:author
|
gptkb:David_Silver
gptkb:Bilal_Piot
gptkb:Dan_Horgan
gptkb:Georg_Ostrovski
gptkb:Hado_van_Hasselt
gptkb:Joseph_Modayil
gptkb:Matteo_Hessel
gptkb:Mohammad_Azar
gptkb:Tom_Schaul
gptkb:Will_Dabney
|
|
gptkbp:category
|
model-free RL
value-based RL
|
|
gptkbp:codeAvailable
|
https://github.com/Kaixhin/Rainbow
|
|
gptkbp:combines
|
gptkb:DQN
gptkb:Double_DQN
gptkb:Prioritized_Experience_Replay
gptkb:Distributional_RL
gptkb:Dueling_Network_Architectures
gptkb:Noisy_Nets
Multi-step Learning
|
|
gptkbp:developedBy
|
gptkb:DeepMind
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Rainbow DQN
|
|
gptkbp:improves
|
gptkb:DQN
gptkb:Double_DQN
gptkb:Dueling_DQN
gptkb:Distributional_DQN
gptkb:Noisy_DQN
gptkb:Prioritized_DQN
|
|
gptkbp:introducedIn
|
2017
|
|
gptkbp:language
|
gptkb:Python
|
|
gptkbp:notablePublication
|
gptkb:Rainbow:_Combining_Improvements_in_Deep_Reinforcement_Learning
|
|
gptkbp:openSource
|
true
|
|
gptkbp:publishedIn
|
gptkb:AAAI_2018
|
|
gptkbp:url
|
https://arxiv.org/abs/1710.02298
|
|
gptkbp:uses
|
gptkb:Q-learning
|
|
gptkbp:bfsParent
|
gptkb:Deep_Q-Network
gptkb:Deep_Q-Network_(DQN)
|
|
gptkbp:bfsLayer
|
6
|