Reinforcement Learning Based Personalized Neural Dialogue Generation.
Tulika SahaSaraansh ChopraSriparna SahaPushpak BhattacharyyaPublished in: ICONIP (4) (2020)
Keyphrases
- reinforcement learning
- fitted q iteration
- network architecture
- dialogue system
- function approximation
- neural network
- optimal policy
- user modeling
- human machine
- machine learning
- learning algorithm
- model free
- user profiles
- markov decision processes
- multi agent
- conversational agent
- adaptive learning
- robotic control
- transfer learning
- context aware
- state space
- bio inspired
- personalized information
- biologically plausible
- mixed initiative
- neural model
- partially observable
- learning rules
- natural language
- e learning
- associative memory
- user model
- learning problems
- dynamic programming