Adversarial learning of neural user simulators for dialogue policy optimisation.
Simon KeizerCaroline DockesNorbert BraunschweilerSvetlana StoyanchevRama DoddipatlaPublished in: CoRR (2023)
Keyphrases
- learning algorithm
- action selection
- reinforcement learning
- neural network
- genetic algorithm
- knowledge acquisition
- online learning
- supervised learning
- learning process
- end users
- learning environment
- user interaction
- learning systems
- user satisfaction
- learning rules
- search engine
- knowledge level
- mixed initiative
- conversational agent
- neural computation