Thomas Hubert
Google DeepMind (United Kingdom) · 16 works · 15,676 citations · h-index 11
Top works
- Mastering the game of Go without human knowledge
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- Mastering Atari, Go, chess and shogi by planning with a learned model
- Discovering faster matrix multiplication algorithms with reinforcement learning
- Faster sorting algorithms discovered using deep reinforcement learning
- Monte-Carlo Tree Search as Regularized Policy Optimization
- Olympiad-level formal mathematical reasoning with reinforcement learning
- Online and Offline Reinforcement Learning by Planning with a Learned Model
- Learning and Planning in Complex Action Spaces
- Approximate Exploitability: Learning a Best Response
- Advancing mathematics research with AI-driven formal proof search
- Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics