Yuandong Tian
Yuandong Tian is a research scientist and manager at Meta AI (formerly Facebook AI Research). His research interests span reinforcement learning, game search, system optimization and machine learning.
Timeline (last 90 days)
Yuandong Tian shared core insights on transferring reinforcement learning from game search to system optimization at the NeurIPS 2021 MLFS workshop.
Using machine learning to learn heuristics for system optimization has been proven feasible, but still faces three major challenges: a huge state-action space, many relevant actions, and slow evaluation.
All Facts (3)
田渊栋曾在Meta的FAIR实验室长期从事深度强化学习和博弈论AI研究，在围棋AI、星际争霸AI等项目中有重要贡献
85%UnverifiedUsing machine learning to learn heuristics for system optimization has been proven feasible, but still faces three major challenges: a huge state-action space, many relevant actions, and slow evaluation.
50%UnverifiedYuandong Tian shared core insights on transferring reinforcement learning from game search to system optimization at the NeurIPS 2021 MLFS workshop.
50%