Sven Mika
TalkRL: The Reinforcement Learning Podcast
00:00
The Challenges of Recommendation Systems
When i think of recommender systems, i often think of the one step case. But we still see a lot of company trying bandits as a single step kind of lick. How do you program the user into the similator? And this is one of the difficulties for us at any scale. It's hard to predict when everything goes expdential.
Play episode from 14:47
Transcript
