Lex Fridman Podcast #86 – David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning
43 snips
Apr 3, 2020 
David Silver, a lead researcher at DeepMind, dives into the revolutionary world of reinforcement learning, having pioneered breakthroughs with AlphaGo and AlphaZero. He shares his journey from childhood programming to mastering AI strategies, highlighting the complexities of the game Go. The conversation explores the transformative power of self-play in AI learning, the emotional impact of AlphaGo's historic win against Lee Sedol, and the philosophical implications of defining rewards in artificial systems. Silver's insights challenge our understanding of intelligence in machines.
AI Snips
Chapters
Books
Transcript
Episode notes
First Program
- David Silver's first program displayed his name in various colors on a BBC Model B microcomputer.
- His father, inspired by the machine, shifted careers to study AI, exposing young David to Prolog and family tree queries.
Early Game AI
- During his work in the games industry, David Silver created AIs that could outperform him in specific scenarios.
- However, these handcrafted agents relied on speed and pattern exploitation rather than true intelligence.
First Go Program
- David Silver's first Go program, built using reinforcement learning, learned by trial and error and self-play.
- This program eventually surpassed his own Go skills, giving him satisfaction that a self-learning system could achieve such a feat.
