gptkbp:instanceOf
|
reinforcement learning algorithm
|
gptkbp:author
|
gptkb:Koray_Kavukcuoglu
gptkb:Volodymyr_Mnih
gptkb:Ioannis_Antonoglou
gptkb:Martin_Riedmiller
gptkb:David_Silver
gptkb:Alex_Graves
gptkb:Daan_Wierstra
|
gptkbp:basedOn
|
gptkb:Q-learning
|
gptkbp:category
|
model-free RL
off-policy RL
value-based method
|
gptkbp:citation
|
gptkb:Mnih_et_al.,_2015,_Nature
highly cited
|
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 (DQN)
|
gptkbp:influenced
|
gptkb:Double_DQN
gptkb:Dueling_DQN
gptkb:Prioritized_Experience_Replay
gptkb:Rainbow_DQN
|
gptkbp:input
|
raw pixels
|
gptkbp:introducedIn
|
2013
|
gptkbp:notableAchievement
|
human-level control in Atari games
|
gptkbp:notablePublication
|
gptkb:Playing_Atari_with_Deep_Reinforcement_Learning
|
gptkbp:openSource
|
gptkb:OpenAI_Baselines
gptkb:Stable_Baselines
gptkb:PyTorch_Lightning
gptkb:TensorFlow_Agents
|
gptkbp:output
|
Q-values
|
gptkbp:publishedIn
|
gptkb:Nature
|
gptkbp:relatedTo
|
gptkb:Q-learning
Actor-Critic Methods
Deep Reinforcement Learning
Policy Gradient Methods
|
gptkbp:solvedBy
|
gptkb:Atari_2600_games
|
gptkbp:uses
|
gptkb:model
stochastic gradient descent
experience replay
target network
epsilon-greedy policy
|
gptkbp:bfsParent
|
gptkb:DeepMind
gptkb:reinforcement_learning
|
gptkbp:bfsLayer
|
5
|