Towards integrated dialogue policy learning for multiple domains and intents using Hierarchical Deep Reinforcement Learning.
Tulika SahaDhawal GuptaSriparna SahaPushpak BhattacharyyaPublished in: Expert Syst. Appl. (2020)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- supervised learning
- optimal policy
- action selection
- knowledge acquisition
- actor critic
- multiple domains
- unsupervised learning
- data sets
- data points
- function approximation
- knowledge transfer
- similarity measure
- partially observable
- information retrieval
- databases