Published Apr 3, 2020

David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86

David Silver, a leading AI researcher from DeepMind, delves into the groundbreaking advancements of deep reinforcement learning through systems like AlphaGo and AlphaZero, discussing their innovative self-learning mechanisms, creative cognitive abilities, and the landmark achievements that have reshaped AI's impact on society.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

Michael Littman: Reinforcement Learning and the Future of AI | Lex Fridman Podcast #144
Answers 383 questions
Sergey Levine: Robotics and Machine Learning | Lex Fridman Podcast #108
Answers 383 questions
Andrew Ng: Deep Learning, Education, and Real-World AI | Lex Fridman Podcast #73
Answers 383 questions
Demis Hassabis: DeepMind - AI, Superintelligence & the Future of Humanity | Lex Fridman Podcast #299
Answers 383 questions
Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15
Answers 383 questions
Daniel Kahneman: Thinking Fast and Slow, Deep Learning, and AI | Lex Fridman Podcast #65
Answers 383 questions
Garry Kasparov: Chess, Deep Blue, AI, and Putin | Lex Fridman Podcast #46
Answers 383 questions
Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94
Answers 383 questions
Yann LeCun: Deep Learning, ConvNets, and Self-Supervised Learning | Lex Fridman Podcast #36
Answers 383 questions
Oriol Vinyals: DeepMind AlphaStar, StarCraft, and Language | Lex Fridman Podcast #20
Answers 383 questions
Ben Goertzel: Artificial General Intelligence | Lex Fridman Podcast #103
Answers 383 questions
Michael I. Jordan: Machine Learning, Recommender Systems, and Future of AI | Lex Fridman Podcast #74
Answers 383 questions
Gary Marcus: Toward a Hybrid of Deep Learning and Symbolic AI | Lex Fridman Podcast #43
Answers 383 questions
Peter Norvig: Artificial Intelligence: A Modern Approach | Lex Fridman Podcast #42
Answers 383 questions
Pieter Abbeel: Deep Reinforcement Learning | Lex Fridman Podcast #10
Answers 383 questions

Dexa/Lex Fridman

David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86

Topics covered

Popular Clips

Beyond AlphaGo

Self-Correcting Systems

Defining Intelligence Goals

Early AI Fascination

Creativity in AI

AlphaGo's Confidence Game

AI and Human Triumphs

Infinite Progress

Learning in Complexity

Learning in AI

Intuition in Go

Self-Play in AI

Mastering the Game

Self Play in AI

Complexity of Go

Episode Highlights

Deep Reinforcement Learning

Self Play Mechanisms

Intelligence and Creativity

AlphaGo's Impact

Related Episodes

Michael Littman: Reinforcement Learning and the Future of AI | Lex Fridman Podcast #144

Sergey Levine: Robotics and Machine Learning | Lex Fridman Podcast #108

Andrew Ng: Deep Learning, Education, and Real-World AI | Lex Fridman Podcast #73

Demis Hassabis: DeepMind - AI, Superintelligence & the Future of Humanity | Lex Fridman Podcast #299

Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15

Daniel Kahneman: Thinking Fast and Slow, Deep Learning, and AI | Lex Fridman Podcast #65

Garry Kasparov: Chess, Deep Blue, AI, and Putin | Lex Fridman Podcast #46

Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94

Yann LeCun: Deep Learning, ConvNets, and Self-Supervised Learning | Lex Fridman Podcast #36

Oriol Vinyals: DeepMind AlphaStar, StarCraft, and Language | Lex Fridman Podcast #20

Ben Goertzel: Artificial General Intelligence | Lex Fridman Podcast #103

Michael I. Jordan: Machine Learning, Recommender Systems, and Future of AI | Lex Fridman Podcast #74

Gary Marcus: Toward a Hybrid of Deep Learning and Symbolic AI | Lex Fridman Podcast #43

Peter Norvig: Artificial Intelligence: A Modern Approach | Lex Fridman Podcast #42

Pieter Abbeel: Deep Reinforcement Learning | Lex Fridman Podcast #10

David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86

Topics covered

Popular Clips

Episode Highlights

Deep Reinforcement Learning

Self Play MechanismsThe exploration of self play in AI highlights its transformative potential in developing intelligent systems. David Silver discusses how this approach enables AI to learn independently, paving the way for more adaptable and robust technologies.

Self Play Mechanisms

Intelligence and Creativity

AlphaGo's ImpactAlphaGo's victory over Lee Sedol stands as a landmark achievement in AI, showcasing the profound impact of machine learning on human endeavors. David Silver reflects on the unexpected global significance of this event and the innovative breakthroughs that made it possible.

AlphaGo's Impact

Related Episodes