Reward Shaping for User Satisfaction in a REINFORCE Recommender.
Konstantina ChristakopoulouCan XuSai ZhangSriraj BadamTrevor PotterDaniel LiHao WanXinyang YiYa LeChris BergEric Bencomo DixonEd H. ChiMinmin ChenPublished in: CoRR (2022)
Keyphrases
- user satisfaction
- reward shaping
- reinforcement learning
- complex domains
- information systems
- recommender systems
- reinforcement learning algorithms
- collaborative filtering
- service quality
- markov decision problems
- state space
- markov decision processes
- user perceptions
- structural equation modeling
- reward function
- perceived usefulness
- kolmogorov smirnov
- function approximation
- learning capabilities
- information quality
- temporal difference
- objective measures
- linear programming
- bayesian networks
- machine learning