Natasha Jaques 2
TalkRL: The Reinforcement Learning Podcast
00:00
Adaptive Online Generalization for Self Driving Cars
A big component of human intelligence is that we rely so heavily on social learning. We discover almost nothing completely independently, like look at research right so much of it is reading what everyone else has done and then making a tiny tweak on top. I also see social learning as a path to address this sort of like truck on truck on truck problem we were talking about earlier. Like you kind of need adaptive online generalization to solve some of these safety critical problems.
Transcript
Play full episode
