Sparse Approximate Dynamic Programming for Dialog Management - CentraleSupélec Access content directly
Conference Papers Year : 2010

Sparse Approximate Dynamic Programming for Dialog Management

Senthilkumar Chandramohan
  • Function : Author
  • PersonId : 888330
Matthieu Geist
Olivier Pietquin

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.
No file

Dates and versions

hal-00553180 , version 1 (06-01-2011)

Identifiers

  • HAL Id : hal-00553180 , version 1

Cite

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

Share

Gmail Mastodon Facebook X LinkedIn More