Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning.
Sen ZhaoWei WeiYifan LiuZiyang WangWendi LiXian-Ling MaoShuai ZhuMinghui YangZujie WenPublished in: IJCAI (2023)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- optimal policy
- state space
- supervised learning
- partially observable domains
- policy search
- temporal difference learning
- function approximators
- higher order
- collaborative filtering
- machine learning
- learning systems
- pairwise
- action selection
- reinforcement learning algorithms
- user profiles
- actor critic
- inverse reinforcement learning
- partially observable environments
- prior knowledge