AlphaGo Zero
Study / Research
AI reinforcement learning milestone discussed as an example of learning rules applied to complex tasks.
Mentioned in 4 videos
Videos Mentioning AlphaGo Zero
How Dopamine & Serotonin Shape Decisions, Motivation & Learning | Dr. Read Montague
Andrew Huberman
AI reinforcement learning milestone discussed as an example of learning rules applied to complex tasks.
Sean Kelly: Existentialism, Nihilism, and the Search for Meaning | Lex Fridman Podcast #227
Lex Fridman
A version of DeepMind's AlphaGo that learned Go entirely from self-play, mentioned as an example of AI surprising humans in game-playing, preceding AlphaZero.
Michael Littman: Reinforcement Learning and the Future of AI | Lex Fridman Podcast #144
Lex Fridman
An advanced version of AlphaGo that learned to play Go purely through self-play, without human expert games, which Satinder Singh found breathtaking.
Demis Hassabis: DeepMind - AI, Superintelligence & the Future of Humanity | Lex Fridman Podcast #299
Lex Fridman
An AI system developed by DeepMind that learned to play Go better than any human by playing against itself.