awarebayes / RecNN

Reinforced Recommendation toolkit built around pytorch 1.7
Apache License 2.0
577 stars 114 forks source link

Hi , can you please provide the same for Proximal policy optimization algorithm based recommendation . Thanks #21

Closed conely89 closed 3 years ago

awarebayes commented 3 years ago

Hello, PPO is an online learning algorithm, whereas I focus more on offline learning in this repository given the nature of these recommendations. You can easily implement PPO algorithm yourself if you want to