Hado van Hasselt
E441099
Hado van Hasselt is a researcher in reinforcement learning best known for pioneering methods such as Double Q-learning and Dueling DQN that address overestimation bias and improve deep RL performance.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Hado van Hasselt canonical | 3 |
How this entity was disambiguated
This entity first appeared as the object of triple T4470153 — 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: Hado van Hasselt Context triple: [Dueling DQN, introducedBy, Hado van Hasselt]
-
A.
Maarten ’t Hart
Maarten ’t Hart is a Dutch writer and biologist known for his psychologically rich novels and essays, often drawing on his strict religious upbringing and love of classical music.
-
B.
Hendrik van den Bergh
Hendrik van den Bergh was a 17th-century Dutch-born nobleman and military commander who served the Spanish Habsburgs during the Eighty Years' War.
-
C.
Dignom Cornelisdr de Haes
Dignom Cornelisdr de Haes was a Dutch woman of the 17th century best known as the mother of the famed admiral Cornelis Tromp.
-
D.
Yorick van Wageningen
Yorick van Wageningen is a Dutch actor known internationally for his roles in films such as the 2011 adaptation of "The Girl with the Dragon Tattoo."
-
E.
Goris van der Heyden
Goris van der Heyden was a member of the Dutch van der Heyden family, known primarily as the son of the renowned 17th-century painter and inventor Jan van der Heyden.
- 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: Hado van Hasselt Target entity description: Hado van Hasselt is a researcher in reinforcement learning best known for pioneering methods such as Double Q-learning and Dueling DQN that address overestimation bias and improve deep RL performance.
-
A.
Maarten ’t Hart
Maarten ’t Hart is a Dutch writer and biologist known for his psychologically rich novels and essays, often drawing on his strict religious upbringing and love of classical music.
-
B.
Hendrik van den Bergh
Hendrik van den Bergh was a 17th-century Dutch-born nobleman and military commander who served the Spanish Habsburgs during the Eighty Years' War.
-
C.
Dignom Cornelisdr de Haes
Dignom Cornelisdr de Haes was a Dutch woman of the 17th century best known as the mother of the famed admiral Cornelis Tromp.
-
D.
Yorick van Wageningen
Yorick van Wageningen is a Dutch actor known internationally for his roles in films such as the 2011 adaptation of "The Girl with the Dragon Tattoo."
-
E.
Goris van der Heyden
Goris van der Heyden was a member of the Dutch van der Heyden family, known primarily as the son of the renowned 17th-century painter and inventor Jan van der Heyden.
- F. None of above. chosen
Statements (46)
| Predicate | Object |
|---|---|
| instanceOf |
artificial intelligence researcher
ⓘ
computer scientist ⓘ person ⓘ reinforcement learning researcher ⓘ |
| citizenship | Netherlands NERFINISHED ⓘ |
| coDeveloped | Dueling DQN architecture NERFINISHED ⓘ |
| developed |
Double DQN algorithm
NERFINISHED
ⓘ
Double Q-learning algorithm NERFINISHED ⓘ |
| educatedAt | Utrecht University NERFINISHED ⓘ |
| employer | Google DeepMind NERFINISHED ⓘ |
| fieldOfWork |
artificial intelligence
ⓘ
machine learning ⓘ reinforcement learning ⓘ |
| hasAcademicDegree | PhD in computer science ⓘ |
| hasPublicationType |
conference papers
ⓘ
journal articles ⓘ |
| hasRole | senior research scientist at DeepMind ⓘ |
| influencedBy |
Q-learning
NERFINISHED
ⓘ
temporal-difference learning methods ⓘ |
| knownFor |
Double DQN
NERFINISHED
ⓘ
Double Q-learning NERFINISHED ⓘ Dueling DQN NERFINISHED ⓘ deep reinforcement learning algorithms ⓘ reducing overestimation bias in Q-learning ⓘ |
| languageSpoken |
Dutch
ⓘ
English ⓘ |
| memberOf | DeepMind NERFINISHED ⓘ |
| nationality | Dutch ⓘ |
| notableWork |
Deep Reinforcement Learning with Double Q-learning
NERFINISHED
ⓘ
Double Q-learning: Mitigating the overestimation bias in Q-learning NERFINISHED ⓘ Dueling Network Architectures for Deep Reinforcement Learning NERFINISHED ⓘ |
| occupation |
research scientist
ⓘ
researcher ⓘ |
| publishedIn |
AAAI
NERFINISHED
ⓘ
ICML NERFINISHED ⓘ JMLR NERFINISHED ⓘ NeurIPS NERFINISHED ⓘ |
| researchInterest |
deep reinforcement learning
ⓘ
exploration in reinforcement learning ⓘ off-policy learning ⓘ temporal-difference learning ⓘ value-based reinforcement learning ⓘ |
| thesisTopic | reinforcement learning ⓘ |
| worksOn |
applications of RL to games
ⓘ
scalable deep RL algorithms ⓘ stability and bias in value estimation ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Hado van Hasselt Description of subject: Hado van Hasselt is a researcher in reinforcement learning best known for pioneering methods such as Double Q-learning and Dueling DQN that address overestimation bias and improve deep RL performance.
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.