
#3: Bandits and Simulators for Recommenders with Olivier Jeunen
Recsperts - Recommender Systems Experts
Castle, Inference and Machine Learning
I remember that workshop from this year's Reksoz where we're talking about off-policy evaluation and off-policy learning. So it was awesome to follow that workshop because it really blew my mind and there were so many things. And they actually also came up with that open-bended or referred to open- bended pipeline, which is a type of recommendation system. We prove in the paper that when you really don't make any assumptions, it can be possible to learn certain effects on user behavior.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.