Investigating Deep Reinforcement Learning Techniques in Personalized Dialogue Generation.
Min YangQiang QuKai LeiJia ZhuZhou ZhaoXiaojun ChenJoshua Zhexue HuangPublished in: SDM (2018)
Keyphrases
- reinforcement learning
- function approximation
- mixed initiative
- dialogue system
- learning process
- adaptive learning
- user modeling
- learning environment
- human computer
- user profiles
- optimal policy
- markov decision processes
- learning algorithm
- learning problems
- spoken language
- personalized recommendation
- temporal difference
- mobile robot
- e learning