Dueling DQN

E98474

Deep Q-Network variant deep reinforcement learning algorithm value-based reinforcement learning method

Dueling DQN is a deep reinforcement learning algorithm that separates state-value and advantage estimations within its neural network architecture to improve learning efficiency and stability over standard DQN.

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

All labels observed (4)

Label	Occurrences
Dueling DQN canonical	4
Dueling Deep Q-Network	1
Dueling Double DQN	1
Dueling Network Architectures for Deep Reinforcement Learning	1

How this entity was disambiguated

This entity first appeared as the object of triple T824084 — 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: Dueling DQN
Context triple: [OpenAI Baselines, implementsAlgorithm, Dueling DQN]

A. Atari deep Q-network
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.
B. MuZero
MuZero is a DeepMind reinforcement learning algorithm that learns to plan and master complex games like Go, chess, and Atari without being given the rules in advance.
C. DRL
DRL is the U.S. State Department bureau responsible for promoting democracy, protecting human rights, and advancing labor rights worldwide.
D. Arcade Learning Environment
Arcade Learning Environment is a widely used research platform that provides a suite of Atari 2600 games for developing and evaluating reinforcement learning algorithms.
E. OpenAI Baselines
OpenAI Baselines is a collection of high-quality reference implementations of reinforcement learning algorithms released by OpenAI for research and benchmarking.
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: Dueling DQN
Target entity description: Dueling DQN is a deep reinforcement learning algorithm that separates state-value and advantage estimations within its neural network architecture to improve learning efficiency and stability over standard DQN.

A. Atari deep Q-network
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.
B. MuZero
MuZero is a DeepMind reinforcement learning algorithm that learns to plan and master complex games like Go, chess, and Atari without being given the rules in advance.
C. DRL
DRL is the U.S. State Department bureau responsible for promoting democracy, protecting human rights, and advancing labor rights worldwide.
D. Arcade Learning Environment
Arcade Learning Environment is a widely used research platform that provides a suite of Atari 2600 games for developing and evaluating reinforcement learning algorithms.
E. OpenAI Baselines
OpenAI Baselines is a collection of high-quality reference implementations of reinforcement learning algorithms released by OpenAI for research and benchmarking.
F. None of above. chosen

Statements (44)

Predicate	Object
instanceOf	Deep Q-Network variant ⓘ deep reinforcement learning algorithm ⓘ value-based reinforcement learning method ⓘ
actionSpaceType	discrete ⓘ
aimsToImprove	learning efficiency ⓘ training stability ⓘ
basedOn	Q-learning ⓘ
citationVenue	ICML ⓘ surface form: Proceedings of the 33rd International Conference on Machine Learning
combinesStreamsToEstimate	Q-values ⓘ
commonlyEvaluatedOn	Atari 2600 ⓘ surface form: Atari 2600 games
controlType	off-policy ⓘ
domain	artificial intelligence ⓘ
especiallyHelpsWhen	many actions have similar value ⓘ only a few actions affect the value of the state ⓘ
extends	Atari deep Q-network ⓘ surface form: Deep Q-Network
field	reinforcement learning ⓘ
hasComponent	advantage stream ⓘ value stream ⓘ
hasFullName	Dueling DQN self-linksurface differs ⓘ surface form: Dueling Deep Q-Network
hasKeyIdea	decouple representation of state value from representation of advantages for each action ⓘ
implementedIn	DeepMind Atari agent ⓘ
improvesOver	Atari deep Q-network ⓘ surface form: standard DQN
influenced	Rainbow DQN ⓘ
introducedBy	Hado van Hasselt ⓘ Marc Lanctot ⓘ Matteo Hessel ⓘ Nando de Freitas ⓘ Tom Schaul ⓘ Ziyu Wang ⓘ
introducedInPaper	Dueling DQN self-linksurface differs ⓘ surface form: Dueling Network Architectures for Deep Reinforcement Learning
learningParadigm	model-free ⓘ
normalizesAdvantageStream	by subtracting mean advantage ⓘ
oftenCombinedWith	Double DQN ⓘ Prioritized Experience Replay DQN ⓘ surface form: Prioritized Experience Replay
publishedAtConference	ICML ⓘ surface form: ICML 2016
separatesEstimationOf	advantage function ⓘ state-value function ⓘ
sharesFeatureExtractor	between value and advantage streams ⓘ
usesFunctionApproximator	deep neural network ⓘ
usesLossFunction	temporal-difference loss ⓘ
usesOptimizationMethod	Adam optimizer ⓘ stochastic gradient descent ⓘ
usesTargetNetwork	yes ⓘ
yearIntroduced	2016 ⓘ

How these facts were elicited

Referenced by (7)

Full triples — surface form annotated when it differs from this entity's canonical label.

OpenAI Baselines → implementsAlgorithm → Dueling DQN ⓘ

Atari deep Q-network → inspiredAlgorithm → Dueling DQN ⓘ

Dueling DQN → hasFullName → Dueling DQN self-linksurface differs ⓘ

this entity surface form: Dueling Deep Q-Network

Dueling DQN → introducedInPaper → Dueling DQN self-linksurface differs ⓘ

this entity surface form: Dueling Network Architectures for Deep Reinforcement Learning

Prioritized Experience Replay DQN → compatibleWith → Dueling DQN ⓘ

Double DQN → influenced → Dueling DQN ⓘ

this entity surface form: Dueling Double DQN

Rainbow DQN → improvesOver → Dueling DQN ⓘ

All labels observed (4)

How this entity was disambiguated Show

Statements (44)

How these facts were elicited Show

Referenced by (7)

How this entity was disambiguated

How these facts were elicited