Published Dec 16, 2018

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

Renowned robotics researcher Pieter Abbeel delves into the transformative world of deep reinforcement learning, discussing how robots can learn and form connections through advanced techniques, the impact of self-play and simulation, and the future of AI with modular systems.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

Sergey Levine: Robotics and Machine Learning | Lex Fridman Podcast #108
Answers 383 questions
Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics | Lex Fridman Podcast #15
Answers 383 questions
Andrew Ng: Deep Learning, Education, and Real-World AI | Lex Fridman Podcast #73
Answers 383 questions
Peter Norvig: Artificial Intelligence: A Modern Approach | Lex Fridman Podcast #42
Answers 383 questions
Michael Littman: Reinforcement Learning and the Future of AI | Lex Fridman Podcast #144
Answers 383 questions
Pieter Levels: Programming, Viral AI Startups, and Digital Nomad Life | Lex Fridman Podcast #440
Answers 383 questions
Yann LeCun: Deep Learning, ConvNets, and Self-Supervised Learning | Lex Fridman Podcast #36
Answers 383 questions
Rodney Brooks: Robotics | Lex Fridman Podcast #217
Answers 383 questions
David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning | Lex Fridman Podcast #86
Answers 383 questions
Anca Dragan: Human-Robot Interaction and Reward Engineering | Lex Fridman Podcast #81
Answers 383 questions
Matt Botvinick: Neuroscience, Psychology, and AI at DeepMind | Lex Fridman Podcast #106
Answers 383 questions
François Chollet: Keras, Deep Learning, and the Progress of AI | Lex Fridman Podcast #38
Answers 383 questions
Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94
Answers 383 questions
Yoshua Bengio: Deep Learning | Lex Fridman Podcast #4
Answers 383 questions
Rana el Kaliouby: Emotion AI, Social Robots, and Self-Driving Cars | Lex Fridman Podcast #322
Answers 383 questions

Dexa/Lex Fridman

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

Topics covered

Popular Clips

Mastering Generalization

Learning from Feedback

Hierarchical Learning Insights

Reinforcement Learning Insights

Robot Psychology

Teaching Robots Skills

Brain Modularity Insights

Robot Parkour Abilities

Robot Safety Testing

Leapfrogging Experimentation

Power of Simulation

Teaching Robots Kindness

Hierarchical Reasoning Challenges

Episode Highlights

Robot Learning

Reinforcement Learning

Simulation and Modularity

Related Episodes

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

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

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

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

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

Pieter Levels: Programming, Viral AI Startups, and Digital Nomad Life | Lex Fridman Podcast #440

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

Rodney Brooks: Robotics | Lex Fridman Podcast #217

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

Anca Dragan: Human-Robot Interaction and Reward Engineering | Lex Fridman Podcast #81

Matt Botvinick: Neuroscience, Psychology, and AI at DeepMind | Lex Fridman Podcast #106

François Chollet: Keras, Deep Learning, and the Progress of AI | Lex Fridman Podcast #38

Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94

Yoshua Bengio: Deep Learning | Lex Fridman Podcast #4

Rana el Kaliouby: Emotion AI, Social Robots, and Self-Driving Cars | Lex Fridman Podcast #322

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

Topics covered

Popular Clips

Episode Highlights

Robot LearningPieter Abbeel, a leading researcher in robotics, discusses how robots can learn skills through imitation and feedback. He highlights the potential for robots to form emotional connections with humans, akin to pets, through advanced learning techniques.

Robot Learning

Reinforcement Learning

Simulation and ModularityThe discussion shifts to the power of simulation in robotics and how brain modularity can inspire AI development. Pieter Abbeel shares insights on using simulation for training robots and the potential of modular AI systems to enhance learning and adaptability.

Simulation and Modularity

Related Episodes