Curiosity-driven Reinforcement Learning for Dialogue Management.
Paula WesselmannYen-Chen WuMilica GasicPublished in: ICASSP (2019)
Keyphrases
- dialogue management
- reinforcement learning
- learning agent
- dialogue system
- spoken dialogue systems
- natural language generation
- function approximation
- state space
- language understanding
- partially observable markov decision process
- model free
- machine learning
- markov decision processes
- transfer learning
- temporal difference
- optimal policy
- optimal control
- reinforcement learning algorithms
- learning capabilities
- function approximators
- learning process
- user interface
- virtual humans
- partially observable
- multi agent systems