Composite Task-Completion Dialogue System via Hierarchical Deep Reinforcement Learning.
Baolin PengXiujun LiLihong LiJianfeng GaoAsli CelikyilmazSungjin LeeKam-Fai WongPublished in: CoRR (2017)
Keyphrases
- function approximation
- dialogue system
- reinforcement learning
- dialogue management
- human computer
- natural language
- natural language generation
- temporal difference
- mixed initiative
- spoken language
- spoken dialogue systems
- human robot
- model free
- linguistic knowledge
- reinforcement learning algorithms
- natural language understanding
- language understanding
- tutorial dialogue
- state space
- multi agent
- transfer learning
- dialogue manager
- user model
- human users
- semantic analysis
- machine learning
- intelligent tutoring systems
- markov decision processes
- optimal policy
- domain specific
- mobile robot
- dynamic programming
- learning process
- learning algorithm