Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback.
Xiao ZhangHaonan JiaHanjing SuWenhan WangJun XuJi-Rong WenPublished in: SIGIR (2021)
Keyphrases
- delayed feedback
- reinforcement learning
- recommender systems
- collaborative filtering
- user preferences
- streaming data
- video streaming
- data streams
- recommendation systems
- real time
- stream processing
- hopf bifurcation
- latent factor models
- causal reasoning
- streaming media
- bandit problems
- continuous stream
- real time streaming
- logical framework
- long run