Atari deep Q-network

E39543

deep Q-network deep reinforcement learning algorithm model-free reinforcement learning method off-policy reinforcement learning method value-based reinforcement learning method

The Atari deep Q-network is a pioneering deep reinforcement learning system that learned to play a wide range of Atari 2600 video games directly from raw pixels at human-level or better performance.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

AI illustration

All labels observed (10)

Label	Occurrences
DQN	5
Deep Q-Network	5
Human-level control through deep reinforcement learning	5
Playing Atari with Deep Reinforcement Learning	3
Atari deep Q-network canonical	2
Playing Atari with deep reinforcement learning	2
DQN (which handles discrete actions)	1
human-level control through deep reinforcement learning	1
standard DQN	1
“Playing Atari with Deep Reinforcement Learning”	1

How this entity was disambiguated

This entity first appeared as the object of triple T307335 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Atari deep Q-network
Context triple: [DeepMind, knownFor, Atari deep Q-network]

A. OpenAI Baselines
OpenAI Baselines is a collection of high-quality reference implementations of reinforcement learning algorithms released by OpenAI for research and benchmarking.
B. DeepMind
DeepMind is a leading artificial intelligence research company renowned for breakthroughs such as AlphaGo and deep reinforcement learning, operating as a subsidiary of Google.
C. “Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
D. DRL
DRL is the U.S. State Department bureau responsible for promoting democracy, protecting human rights, and advancing labor rights worldwide.
E. “A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Atari deep Q-network
Target entity description: The Atari deep Q-network is a pioneering deep reinforcement learning system that learned to play a wide range of Atari 2600 video games directly from raw pixels at human-level or better performance.

A. OpenAI Baselines
OpenAI Baselines is a collection of high-quality reference implementations of reinforcement learning algorithms released by OpenAI for research and benchmarking.
B. DeepMind
DeepMind is a leading artificial intelligence research company renowned for breakthroughs such as AlphaGo and deep reinforcement learning, operating as a subsidiary of Google.
C. “Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
D. DRL
DRL is the U.S. State Department bureau responsible for promoting democracy, protecting human rights, and advancing labor rights worldwide.
E. “A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
F. None of above. chosen

Statements (50)

Predicate	Object
instanceOf	deep Q-network ⓘ deep reinforcement learning algorithm ⓘ model-free reinforcement learning method ⓘ off-policy reinforcement learning method ⓘ value-based reinforcement learning method ⓘ
achievedPerformanceLevel	human-level control on many Atari 2600 games ⓘ
actionSpace	discrete actions ⓘ
basedOnAlgorithm	Q-learning ⓘ
coAuthor	Alex Graves ⓘ Daan Wierstra ⓘ David Silver ⓘ Ioannis Antonoglou ⓘ Koray Kavukcuoglu ⓘ Martin Riedmiller ⓘ
developedBy	DeepMind ⓘ
doesNotUse	game-specific prior knowledge ⓘ hand-crafted features ⓘ
domain	Atari 2600 video games ⓘ
environmentFramework	Arcade Learning Environment ⓘ
evaluationMetric	average score over episodes ⓘ
evaluationSetting	same network architecture across games ⓘ single set of hyperparameters across games ⓘ
firstAuthor	Volodymyr Mnih ⓘ
inputFrameSize	84x84 grayscale images ⓘ
inputFrameStack	4 consecutive frames ⓘ
inputSource	Atari 2600 games ⓘ
inputType	raw pixel images ⓘ
inspiredAlgorithm	Double DQN ⓘ Dueling DQN ⓘ Prioritized Experience Replay ⓘ linked to: Prioritized Experience Replay DQN Rainbow DQN ⓘ
introducedInPaper	Playing Atari with Deep Reinforcement Learning ⓘ linked to: Atari deep Q-network
introducedInYear	2013 ⓘ
journalPublicationYear	2015 ⓘ
learningParadigm	trial-and-error learning ⓘ
notableContribution	demonstrated deep learning can learn control policies directly from high-dimensional sensory input ⓘ introduced target networks for stabilizing deep Q-learning ⓘ popularized experience replay in deep reinforcement learning ⓘ
observationType	screen images only ⓘ
outputType	Q-values for discrete actions ⓘ action-value function ⓘ
publishedInJournal	Nature ⓘ
rewardSignal	game score changes ⓘ
trainingSignal	game score reward ⓘ
usesExplorationStrategy	epsilon-greedy policy ⓘ
usesFunctionApproximator	convolutional neural network ⓘ
usesLossFunction	temporal-difference error ⓘ
usesOptimizationMethod	stochastic gradient descent ⓘ
usesStabilizationTechnique	experience replay ⓘ target network ⓘ

How these facts were elicited