Towards Long-term Fairness in Interactive Recommendation: A Maximum Entropy Reinforcement Learning Approach.
Xiaoyu ShiQuanliang LiuHong XieMingsheng ShangPublished in: ICWS (2023)
Keyphrases
- maximum entropy
- long term
- reinforcement learning
- maximum entropy principle
- markov models
- recommender systems
- probabilistic logic
- minimum cross entropy
- conditional random fields
- random fields
- principle of maximum entropy
- class conditional
- learning algorithm
- maximum entropy model
- transformation based learning
- collaborative filtering
- iterative scaling
- machine learning
- optimal policy
- learning problems
- supervised learning
- image segmentation
- bregman divergences