Thomas Hubert

机构：Google DeepMind (United Kingdom), Google (United Kingdom) · ORCID：0000-0003-2209-3933

发表论文 14 篇 · 总被引 16194 次 · h-index 11

代表论文

• Mastering the game of Go without human knowledge (2017 · Nature · 被引 9370)
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play (2018 · Science · 被引 3636)
• Mastering Atari, Go, chess and shogi by planning with a learned model (RePEc: Research Papers in Economics · 被引 1372)
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017 · arXiv (Cornell University) · 被引 1082)
• Discovering faster matrix multiplication algorithms with reinforcement learning (2022 · Nature · 被引 475)
• Faster sorting algorithms discovered using deep reinforcement learning (2023 · Nature · 被引 176)