A Task-oriented Chatbot Based on LSTM and Reinforcement Learning.
Tai-Liang ChouYu-Ling HsuehPublished in: NLPIR (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- machine learning
- multi agent
- action selection
- optimal policy
- data sets
- policy search
- multi agent reinforcement learning
- temporal difference learning
- learning capabilities
- model free
- description language
- markov decision processes
- learning algorithm
- data mining
- neural network
- recurrent neural networks
- transfer learning
- optimal control
- supervised learning
- active learning
- learning process
- temporal difference
- dialogue system
- case study
- database
- online discussion forums
- robotic control