Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning.
Yang DengYaliang LiFei SunBolin DingWai LamPublished in: SIGIR (2021)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning systems
- policy search
- learning tasks
- optimal policy
- multi modal
- online learning
- active learning
- temporal difference learning
- actor critic
- machine learning
- action selection
- learning agents
- prior knowledge
- partially observable domains
- supervised learning
- transfer learning
- function approximation