Pieter Abbeel: Deep Reinforcement Learning
Lex Fridman Podcast
00:00
The Future of AI Safety?
A lot of people have concerned about safety. How do you think about AI safety? As you build robots that are operating in the physical world, how do you approach this problem in an engineering kind of a systematic way? Of course, simulation comes in a lot there to test in simulation. Self-driving cars or robots could be tested more often,. But still, I feel like we don't have this kind of unit tests or proper tests for robots.
Transcript
Play full episode
