Fast reinforcement learning of dialog strategies.
David GoddeauJoelle PineauPublished in: ICASSP (2000)
Keyphrases
- reinforcement learning
- learning algorithm
- machine learning
- learning agents
- function approximation
- natural language
- dynamic programming
- multi agent systems
- mixed initiative
- evolutionary algorithm
- mobile robot
- robot control
- reinforcement learning algorithms
- temporal difference
- reinforcement learning methods
- real time
- control strategies
- search strategies
- supervised learning
- state space
- user interface
- search algorithm
- neural network