Thore Graepel
artificial intelligence researcher
Facts
13 properties- Instance of
- human
- Employer
- University College London, Google DeepMind (2015–present)[3][4]
- Educated at
- Technische Universität Berlin (?–2002)
- Official website
- iris.ucl.ac.uk[10]
- Website
- iris.ucl.ac.uk
- Doctoral advisor
- Ulrich Kockelkorn, Klaus Obermayer[5][6]
- Doctoral student
- Diana Borsa[8]
- Social media followers
- 1,563[11]
- ThoreG
- Viaf id
- 313563914
🏷️ Also known as
en Thore Graepel
🔖 Identifiers · 11
- ORCID iD
- 0000-0003-3957-0310
- VIAF cluster ID
- 313563914
- GND ID
- 1195185561
- OpenAlex ID
- A5051619646as of 2026-09-23
where from?
- Source
- OpenAlex
- Edition
- 20260923 · as of 2026-09-23
- Licence
- CC0 1.0 Universal
- Bronze
- not in the catalog
- Transform
- 4ort-mint · openalex:20260923 · version not recorded
- DBLP author ID
- g/ThoreGraepel
- DDB person (GND) ID
- 1195185561
- Google Scholar author ID
- PNH24toAAAAJ
- IdRef ID
- 176574492
- MR Author ID
- 689974
- Mathematics Genealogy Project ID
- 242107
- X (Twitter) username
- ThoreG (2009–present)
📚 Sources · 1
📜 Data licence
Source: OpenAlex (openalex.org), snapshot of 2026-09-23. CC0 1.0 Universal. CC0 1.0 Universal · OpenAlex
🔗 Connections
Author of 20
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play,
A multi-agent reinforcement learning model of common-pool resource appropriation,
Biases for Emergent Communication in Multi-agent Reinforcement Learning,
Cooperative AI: machines must learn to find common ground,
Differentiable Game Mechanics,
From motor control to team play in simulated humanoid football,
Human-level performance in 3D multiplayer games with population-based reinforcement learning,
Inequity aversion improves cooperation in intertemporal social dilemmas
+12 more
← Authored by 20
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play,
A multi-agent reinforcement learning model of common-pool resource appropriation,
Biases for Emergent Communication in Multi-agent Reinforcement Learning,
Cooperative AI: machines must learn to find common ground,
Differentiable Game Mechanics,
From motor control to team play in simulated humanoid football,
Human-level performance in 3D multiplayer games with population-based reinforcement learning,
Inequity aversion improves cooperation in intertemporal social dilemmas
+12 more
Affiliated with 5
Employer 3
Occupation 2
Doctoral advisor 1
Doctoral advisors 1
Educated at 1
Given name 1
Instance of 1
Sex or gender 1
Press Enter · cited answer in seconds
0 sources
Summary
Thore Graepel worked as an artificial intelligence researcher[1] and computer scientist[2].
Body
Education
Doctoral advisors include Ulrich Kockelkorn[5], a statistician[12], b. 1941[13], specialised in statistics[14] and Klaus Obermayer[6], an artificial intelligence researcher[15], b. 1961[16], of Germany[17], specialised in computational neuroscience[18].
Career and Affiliations
Employers include University College London[3], a university college[19], in United Kingdom[20], founded in 1826[21], headquartered in UCL Main Building[22] and Google DeepMind[4], a subsidiary company[23], in United Kingdom[24], founded in 2010[25], headquartered in London[26].
FAQs
What did Thore Graepel do for work?
Thore Graepel worked as artificial intelligence researcher[1] and computer scientist[2].