Sparse Approximate Dynamic Programming for Dialog Management

Abstract : Spoken dialogue management strategy optimization by means of Reinforcement Learning (RL) is now part of the state of the art. Yet, there is still a clear mismatch between the complexity implied by the required naturalness of dialogue systems and the inability of standard RL algorithms to scale up. Another issue is the sparsity of the data available for training in the dialogue domain which can not ensure convergence of most of RL algorithms. In this paper, we propose to combine a sample-efficient generalization framework for RL with a feature selection algorithm for the learning of an optimal spoken dialogue management strategy.
Document type :
Conference papers
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00553180
Contributor : Sébastien van Luchene <>
Submitted on : Thursday, January 6, 2011 - 4:35:54 PM
Last modification on : Thursday, March 29, 2018 - 11:06:04 AM

Identifiers

  • HAL Id : hal-00553180, version 1

Collections

Citation

Senthilkumar Chandramohan, Matthieu Geist, Olivier Pietquin. Sparse Approximate Dynamic Programming for Dialog Management. SIGDial 2010, Sep 2010, Tokyo, Japan. pp.107-115. ⟨hal-00553180⟩

Share

Metrics

Record views

36