Thomas Hubert
Source-listed: Research Engineer · Google DeepMind
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning AlgorithmSaved credit: Contributor · 2017Explore people connected to this work →
- Mastering Atari, Go, Chess and Shogi by Planning with a Learned ModelSaved credit: Contributor · 2019Explore people connected to this work →
- Learning and Planning in Complex Action SpacesSaved credit: First author · 2021Explore people connected to this work →
- Discovering faster matrix multiplication algorithms with reinforcement learningSaved credit: Contributor · 2022Explore people connected to this work →
- Olympiad-level formal mathematical reasoning with reinforcement learningSaved credit: First author · 2025Explore people connected to this work →