A Scalable Probabilistic Model for Reward Optimizing Slate Recommendation.
Imad AoualiAchraf Ait Sidi HammouSergey IvanovOtmane SakhiDavid RohdeFlavian VasilePublished in: CoRR (2022)
Keyphrases
- probabilistic model
- recommender systems
- generative model
- collaborative filtering
- language model
- bayesian networks
- reinforcement learning
- user preferences
- databases
- neural network
- highly scalable
- artificial intelligence
- database
- user feedback
- recommendation systems
- information overload
- long run
- inverse reinforcement learning
- music recommendation