Publication

Towards sharing task environments to support reproducible evaluations of interactive recommender systems

Barraza-Urbina, Andrea
; 
d'Aquin, Mathieu
Thumbnail Image
Files
Thumbnail Image
[REVEAL2019]Towards Sharing Task Environments for Interactive RS Evaluation.pdf
Adobe PDF, 512.17 KB
Identifiers
http://hdl.handle.net/10379/15438
Publication Date
2019-09-20
Keywords
Recommender Systems, Recommendation Systems, Reinforcement Learning, Evaluation, Reproducibility
Type
Workshop paper
Downloads
Show all metadata
Citation
Barraza-Urbina, Andrea , & d’Aquin, Mathieu (2019). Towards sharing task environments to support reproducible evaluations of interactive recommender systems. Paper presented at the REVEAL’19, Copenhagen, Denmark, 20 September, DOI: 10.13025/pqjz-f728
Abstract
Beyond sharing datasets or simulations, we believe the Recommender Systems (RS) community should share Task Environments. In this work, we propose a high-level logical architecture that will help to reason about the core components of a RS Task Environment, identify the differences between Environments, datasets and simulations; and most importantly, understand what needs to be shared about Environments to achieve reproducible experiments. The work presents itself as valuable initial groundwork, open to discussion and extensions.
Funder
Science Foundation Ireland
European Regional Development Fund
Publisher
NUI Galway
Publisher DOI
Rights
Attribution-NonCommercial-NoDerivs 3.0 Ireland
cbn
Collections
Data Science Institute (Workshop Papers)