Real World Data
Pieter emphasizes the importance of collecting real-world data for solving robotics problems efficiently. Lukas questions the availability of suitable datasets, prompting Pieter to stress the need for in-distribution data for effective machine learning outcomes in practical applications.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Pieter Abbeel — Robotics, Startups, and Robotics Startups
Related Questions
How is machine learning used in robots as discussed in the episode Pieter Abbeel: Deep Reinforcement Learning | Lex Fridman Podcast #10 and the clip Learning from Feedback?
How is machine learning used in robots as discussed in the episode Pieter Abbeel: Deep Reinforcement Learning | Lex Fridman Podcast #10 and the clip Teaching Robots Skills?
How is machine learning used in robots as discussed in the episode Pieter Abbeel: Deep Reinforcement Learning | Lex Fridman Podcast #10 and the clip Mastering Generalization?