Martin Riedmiller
E200561
Martin Riedmiller is a German computer scientist and pioneer in deep reinforcement learning, known for his influential work on neural-network-based control and contributions to landmark deep RL systems.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Martin Riedmiller canonical | 2 |
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
German person
ⓘ
computer scientist ⓘ person ⓘ researcher ⓘ |
| affiliation | DeepMind ⓘ |
| countryOfAcademicInstitution | Germany ⓘ |
| countryOfResidence | United Kingdom ⓘ |
| employerType | research company ⓘ |
| fieldOfWork |
artificial intelligence
ⓘ
computer science ⓘ deep reinforcement learning ⓘ machine learning ⓘ reinforcement learning ⓘ |
| hasAcademicAdvisor | unknown ⓘ |
| hasAcademicAffiliation | University of Freiburg NERFINISHED ⓘ |
| hasCitizenship | Germany ⓘ |
| hasContribution |
bridging reinforcement learning and control engineering
ⓘ
early practical algorithms for neural-network-based reinforcement learning ⓘ industrial applications of reinforcement learning ⓘ |
| hasEmployer | DeepMind ⓘ |
| hasGender | male ⓘ |
| hasNotableStudent | unknown ⓘ |
| hasOccupation |
artificial intelligence researcher
ⓘ
computer scientist ⓘ machine learning researcher ⓘ |
| hasRole |
research scientist
ⓘ
team lead ⓘ |
| isPioneerIn |
deep reinforcement learning
ⓘ
neural-network-based control ⓘ |
| knownFor |
applications of reinforcement learning to robotics
ⓘ
deep reinforcement learning ⓘ landmark deep reinforcement learning systems ⓘ neural-network-based control ⓘ Neural Architecture Search ⓘ
surface form:
neuroevolution of augmenting topologies for control tasks
work on value function approximation with neural networks ⓘ |
| languageOfWorkOrName |
English
ⓘ
German ⓘ |
| memberOf |
DeepMind
ⓘ
surface form:
DeepMind research team
|
| nationality | German ⓘ |
| notableWork |
neural fitted Q-iteration (NFQ)
ⓘ
work on off-policy reinforcement learning with neural networks ⓘ |
| positionHeld | professor of computer science at University of Freiburg ⓘ |
| researchInterest |
autonomous agents
ⓘ
control ⓘ deep learning ⓘ robotics ⓘ sequential decision making ⓘ |
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.