22_CameraReady_rl4rl-main.pdf
thepatricktran.com/wp-content/uploads/2023/04/22_CameraReady_rl4rl-main.pdf
1 Users
0 Comments
2 Highlights
0 Notes
Tags
Top Highlights
Optimizing Audio Recommendations for the Long-Term
This paper describes efforts at a large audio streaming service to optimize audio recommendations for their contribution to users’ long-term listening habits. We draw inspiration from reinforcement learning (RL), which gives a formal language for studying the problem of learning across users to optimize recurring interaction with individual users.
Ready to highlight and find good content?
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.