Thore Graepel
Thore Graepel,
a German physicist and computer scientist, professor of machine learning at University College London, and research lead at Google DeepMind, where he is involved in the AlphaGo and AlphaZero projects mastering the games of Go, chess and Shogi. Thore Graepel received his Ph.D. in machine learning from TU Berlin in 2001. Before joining DeepMind, he was head of the online services and advertising (OSA) research group at Microsoft Research Cambridge. His research interests include probabilistic models, knowledge representation and reasoning, aspects of behavioural game theory, crowdsourcing, and psychometrics [2]. As a Go player, he was passionate about creating a computer program that plays the game of Go better than the best human players [3], and when joining Google, he was the first guy who lost against the "neural network" [4].
Selected Publications
2000 ...
- Michael Bowling, Johannes Fürnkranz, Thore Graepel, Ron Musick (2006). Machine learning and Games. Machine Learning, Vol. 63, No. 3
2010 ...
- David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, Demis Hassabis (2016). Mastering the game of Go with deep neural networks and tree search. Nature, Vol. 529 » AlphaGo
- Marc Lanctot, Vinícius Flores Zambaldi, Audrunas Gruslys, Angeliki Lazaridou, Karl Tuyls, Julien Pérolat, David Silver, Thore Graepel (2017). A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning. arXiv:1711.00832
- David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel, Demis Hassabis (2017). Mastering the game of Go without human knowledge. Nature, Vol. 550
- David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis (2017). Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. arXiv:1712.01815 » AlphaZero
- David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis (2018). A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, Vol. 362, No. 6419 [6]
External Links
- Thore Graepel
- Thore Graepel | LinkedIn
- Thore Graepel - Google Scholar Citations
- Google’s AlphaGo Trounces Humans—But It Also Gives Them a Boost by Cade Metz, Wired, May 26, 2017
References
- ↑ Thore Graepel
- ↑ Dr Thore Graepel — The Psychometrics Centre
- ↑ Keynote talk - Learning to Play: Machine Learning and Computer Games, AIMSA 2010
- ↑ Google’s AlphaGo Trounces Humans—But It Also Gives Them a Boost by Cade Metz, Wired, May 26, 2017
- ↑ dblp: Thore Graepel
- ↑ AlphaZero: Shedding new light on the grand games of chess, shogi and Go by David Silver, Thomas Hubert, Julian Schrittwieser and Demis Hassabis, DeepMind, December 03, 2018