Improved Consistency in Price Negotiation Dialogue System Using Parameterized Action Space with Generative Adversarial Imitation Learning.
Makoto SatoTomohiro TakagiPublished in: ICICT (2023)
Keyphrases
- dialogue system
- imitation learning
- action space
- reinforcement learning methods
- reinforcement learning
- multi agent
- state space
- natural language
- cooperative
- single agent
- human users
- markov decision processes
- real valued
- generative model
- multi agent systems
- robotic systems
- machine learning
- dynamical systems
- stochastic processes
- domain specific
- user model
- knowledge base