Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning.
Yang DengYaliang LiFei SunBolin DingWai LamPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- action selection
- learning problems
- supervised learning
- partially observable
- learning systems
- partially observable environments
- autonomous learning
- learning capabilities
- recommender systems
- state space
- learning tasks
- optimal policy
- function approximation
- neural network
- multi modal
- actor critic
- policy search
- reinforcement learning problems
- prior knowledge
- policy gradient methods
- model free reinforcement learning