Research data supporting “Dialogue manager domain adaptation using Gaussian process reinforcement learning”
Authors
Publication Date
2016-09-05Publisher
University of Cambridge
Type
Dataset
Metadata
Show full item recordCitation
Gasic, M. (2016). Research data supporting “Dialogue manager domain adaptation using Gaussian process reinforcement learning” [Dataset]. https://doi.org/10.17863/CAM.4190
Description
This dataset correspond to the results presented in Computer Speech and Language article Dialogue manager domain adaptation using Gaussian process reinforcement learning and relates to Figure 7. Two contrasts were presented: Prior and NoPrior. NoPrior[1,2,3] is the data obtained in interaction with Amazon MTurk while training three policies for SFR domain. Prior[1,2,3] is the data obtained while training policy for SFR domain that uses a generic policy as a prior. In each directory there is a call directory with a time stamp in the name which contains session.xml file with the dialogue log and feedback.xml file with the user feedback. Figure 8 is obtained using data previously published at https://www.repository.cam.ac.uk/handle/1810/251169 and Figure 9 is obtained using data previously published at https://www.repository.cam.ac.uk/handle/1810/252636 . This data is released under a Creative Commons CC-BY licence (see https://creativecommons.org/licenses/by/4.0/)
Format
Any xml processing software
Keywords
spoken dialogue systems, reinforcement learning
Relationships
Related dataset: https://www.repository.cam.ac.uk/handle/1810/251169https://www.repository.cam.ac.uk/handle/1810/252636
Publication Reference: https://arxiv.org/abs/1609.02846https://www.repository.cam.ac.uk/handle/1810/261140
Sponsorship
EPSRC [EP/M018946/1]
Identifiers
This record's DOI: https://doi.org/10.17863/CAM.4190
Recommended or similar items
The following licence files are associated with this item: