Arthur Guez

E455377
machine learning researcher person

Arthur Guez is a machine learning researcher known for his contributions to deep reinforcement learning, including co-developing the Double DQN algorithm.

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

All labels observed (1)

Label Occurrences
Arthur Guez canonical 2

How this entity was disambiguated

Statements (32)

Predicate Object
instanceOf machine learning researcher ⓘ
person ⓘ
affiliation DeepMind reinforcement learning team ⓘ
linked to: DeepMind
coAuthorOf Bayes-Adaptive Monte-Carlo Planning and Learning in POMDPs ⓘ
Bayes-Adaptive Planning in Markov Decision Processes ⓘ
linked to: Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

Deep Reinforcement Learning with Double Q-learning ⓘ
linked to: Double DQN

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search ⓘ
Information-Theoretic Regret Bounds for Online Nonparametric Regression ⓘ
Investigating Model-Free Planning in Human Choice Prediction ⓘ
Sample-based Search for Optimal Planning in Markov Decision Processes ⓘ
linked to: Monte Carlo tree search
coAuthorWith David Silver ⓘ
Hado van Hasselt ⓘ
coDeveloperOf Double DQN algorithm ⓘ
linked to: Double DQN
doctoralThesisTopic Bayes-adaptive planning and learning in Markov decision processes ⓘ
educatedAt McGill University ⓘ
employer Google DeepMind ⓘ
linked to: DeepMind
fieldOfWork artificial intelligence ⓘ
deep reinforcement learning ⓘ
machine learning ⓘ
reinforcement learning ⓘ
gender male ⓘ
hasAcademicAdvisor Doina Precup ⓘ
hasCitation Deep Reinforcement Learning with Double Q-learning (2015) ⓘ
linked to: Double DQN
knownFor Double DQN algorithm ⓘ
linked to: Double DQN
memberOf DeepMind ⓘ
nationality French ⓘ
notableWork Deep Reinforcement Learning with Double Q-learning ⓘ
linked to: Double DQN
researchInterest Monte Carlo tree search ⓘ
model-based reinforcement learning ⓘ
planning in reinforcement learning ⓘ
worksOn applications of deep RL to games ⓘ
sample-efficient reinforcement learning ⓘ

How these facts were elicited

Referenced by (2)

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

Double DQN → introducedBy → Arthur Guez ⓘ
AlphaGo Zero → hasAuthor → Arthur Guez ⓘ