The exploration/exploitation trade-off in Reinforcement Learning for dialogue management.
Sebastian VargesGiuseppe RiccardiSilvia QuarteroniAlexei V. IvanovPublished in: ASRU (2009)
Keyphrases
- dialogue management
- reinforcement learning
- learning agent
- dialogue system
- spoken dialogue systems
- natural language generation
- state space
- reinforcement learning algorithms
- partially observable markov decision process
- function approximation
- model free
- learning algorithm
- language understanding
- learning process
- optimal control
- transfer learning
- machine learning
- markov decision processes
- temporal difference
- dynamic programming
- user interface
- multi agent
- action selection
- optimal policy
- human machine interaction
- expert systems