|
gptkbp:instanceOf
|
deep reinforcement learning algorithm
|
|
gptkbp:application
|
gptkb:reinforcement_learning
gptkb:Atari_games
|
|
gptkbp:basedOn
|
gptkb:Deep_Q-Network_(DQN)
|
|
gptkbp:citation
|
high (hundreds)
|
|
gptkbp:codeAvailable
|
gptkb:GitHub
|
|
gptkbp:contribution
|
uses parameterized noise in network weights for exploration
|
|
gptkbp:explorationStrategy
|
noisy networks
|
|
gptkbp:field
|
gptkb:artificial_intelligence
gptkb:machine_learning
|
|
gptkbp:fullName
|
Noisy Deep Q-Network
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Noisy DQN
|
|
gptkbp:introducedIn
|
2017
|
|
gptkbp:organization
|
gptkb:DeepMind
|
|
gptkbp:proposedBy
|
gptkb:Demis_Hassabis
gptkb:Alex_Graves
gptkb:Bilal_Piot
Charles Blundell
Ian Osband
Jacob Menick
Meire Fortunato
Mohammad Gheshlaghi Azar
Olivier Pietquin
Remi Munos
Vlad Mnih
|
|
gptkbp:publicationDate
|
arXiv:1706.10295
|
|
gptkbp:publishedIn
|
Noisy Networks for Exploration
|
|
gptkbp:relatedTo
|
gptkb:Rainbow_DQN
gptkb:Distributional_DQN
Bootstrapped DQN
|
|
gptkbp:replacedBy
|
epsilon-greedy exploration
|
|
gptkbp:bfsParent
|
gptkb:Rainbow_DQN
|
|
gptkbp:bfsLayer
|
7
|