Search Results for author: Fabrice Lefèvre

Found 4 papers, 0 papers with code

Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users

no code implementations25 Oct 2021 Matthieu Riou, Bassam Jabaian, Stéphane Huet, Fabrice Lefèvre

The analysis of these experiments gives us some insights, discussed in the paper, into the difficulty for the system's trainers to establish a coherent and constant behavioural strategy to enable a fast and good-quality training phase.

Dialogue Management Management +3

Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation

no code implementations25 Nov 2020 Thibault Cordier, Tanguy Urvoy, Lina M. Rojas-Barahona, Fabrice Lefèvre

We notably propose a randomised exploration policy which allows for a seamless hybridisation of the learned policy and the expert.

Imitation Learning Q-Learning +1

Joint On-line Learning of a Zero-shot Spoken Semantic Parser and a Reinforcement Learning Dialogue Manager

no code implementations1 Oct 2018 Matthieu Riou, Bassam Jabaian, Stéphane Huet, Fabrice Lefèvre

Several variants of joint learning are investigated and tested with user trials to confirm that the overall on-line learning can be obtained after only a few hundred training dialogues and can overstep an expert-based system.

Dialogue Management Management +3

Cannot find the paper you are looking for? You can Submit a new open access paper.