293: True Personalization Through Reinforcement Learning
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
How to Train a Self-Driving Car
You don't see Tesla or I don't know Waymo that the Google version of self-driving cars. They simulate they have simulated environment, which could be basically an environment where a actual human drove the car and the reinforcement learning agent made decision in the background. And then once you have that, you replay that environment. That's an actual, actual environment that you can use to train your model after the fact. The number of scenarios and any environment that involves human behavior is basically infinite.
Play episode from 46:50
Transcript
