Module 4: Recommender System Application

This module introduces you to working with Recommender Systems in the context of RL.

0Module 4 Learning Outcomes

1Intro to recommender systems

2Benefits of RL for recommendations

3Drawbacks of RL for recommendations

4Recommender systems difficulty

5Recommender env: design

6Big-picture

7Recommender rewards

8Sugar crash

9Recommender env: implementation

10Improving the user model

11Greedy vs. random

12Greedy vs. random continued

13Solving the environment

14Recommender rewards

15Discount factor

16Offline RL

17Example of offline RL

18Does offline data help?

19Historical data policy

About this course

This course teaches you the basics of reinforcement learning in an applied fashion, by leveraging the production-grade RL framework Ray RLlib. Enjoy!

About the team

© 2022. Proudly built by the Ray team. Course platform based on the SpaCy course by Ines Montani.