Scalable Deep Q-Learning for Session-Based Slate Recommendation.
Aayush Singha RoyEdoardo D'AmicoElias Z. TragosAonghus LawlorNeil HurleyPublished in: RecSys (2023)
Keyphrases
- reinforcement learning
- cooperative
- function approximation
- recommender systems
- state space
- multi agent
- learning algorithm
- collaborative filtering
- information retrieval
- deep learning
- lightweight
- web scale
- highly scalable
- action selection
- model free
- data sets
- temporal difference
- reinforcement learning algorithms
- multi agent systems
- stochastic approximation
- potential field