Yang Gao - Sample-efficient AI

Yang Gao, an AI researcher with affiliations at Berkeley and Tsinghua University, joined the podcast to talk integrating reinforcement learning with search methods, EfficientZero and MuZero, and comparing EfficientZero’s sample efficiency to that of a human being. Intro music: ➞ Artist: Ron Gelinas ➞ Track Title: Daybreak Chill Blend (original mix) ➞ Link to Track: 0:00 Intro 1:50 Yang’s background 6:00 MuZero’s activity 13:25 MuZero to EfficiantZero 19:00 Sample efficiency comparison 23:40 Leveraging algorithmic tweaks 27:10 Importance of evolution to human brains and AI systems 35:10 Human-level sample efficiency 38:28 Existential risk from AI in China 47:30 Evolution and language 49:40 Wrap-up