Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning

@inproceedings{Scheffler2002AutomaticLO,
  title={Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning},
  author={K. Scheffler and S. Young},
  year={2002}
}
This paper describes a method for automatic design of human-computer dialogue strategies by means of reinforcement learning, using a dialogue simulation tool to model the user behaviour and system recognition performance. To the authors' knowledge this is the first application of a detailed simulation tool to this problem. The simulation tool is trained on a corpus of real user data. Compared to direct state transition modelling, it has the major advantage that different state space… Expand
A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies
Learning automata-based approach to learn dialogue policies in large state space
Representing the Reinforcement Learning state in a negotiation dialogue
  • P. Heeman
  • Computer Science
  • 2009 IEEE Workshop on Automatic Speech Recognition & Understanding
  • 2009
A Reinforcement Learning approach to evaluating state representations in spoken dialogue systems
Evaluation of a hierarchical reinforcement learning spoken dialogue system
Hybrid reinforcement/supervised learning for dialogue policies from COMMUNICATOR data
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email
  • M. Walker
  • Computer Science
  • J. Artif. Intell. Res.
  • 2000
Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for Email
Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
Planning and Acting under Uncertainty: A New Model for Spoken Dialogue System
User modelling in adaptive dialogue management
A stochastic model of human-machine interaction for learning dialog strategies
Probabilistic methods in spoken–dialogue systems
  • S. Young
  • Computer Science, Biology
  • Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences
  • 2000
Reinforcement Learning for Spoken Dialogue Systems
Fast reinforcement learning of dialog strategies
  • D. Goddeau, Joelle Pineau
  • Computer Science
  • 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
  • 2000
Automatic Optimization of Dialogue Management
...
1
2
3
...