Uncertainty-based Out-of-Distribution Classification in Deep Reinforcement Learning

Andreas Sedlmeier, Thomas Gabor, Thomy Phan, Lenz Belzner, Claudia Linnhoff-Popien

Abstract

Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. As a first step towards a solution, we consider the problem of detecting such data in a value-based deep reinforcement learning (RL) setting. Modelling this problem as a one-class classification problem, we propose a framework for uncertainty-based OOD classification: UBOOD. It is based on the effect that an agent’s epistemic uncertainty is reduced for situations encountered during training (in-distribution), and thus lower than for unencountered (OOD) situations. Being agnostic towards the approach used for estimating epistemic uncertainty, combinations with different uncertainty estimation methods, e.g. approximate Bayesian inference methods or ensembling techniques are possible. Evaluation shows that the framework produces reliable classification results when combined with ensemble-based estimators, while the combination with concrete dropout-based estimators fails to reliably detect OOD situations.

Download


Paper Citation


in Harvard Style

Sedlmeier A., Gabor T., Phan T., Belzner L. and Linnhoff-Popien C. (2020). Uncertainty-based Out-of-Distribution Classification in Deep Reinforcement Learning.In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-395-7, pages 522-529. DOI: 10.5220/0008949905220529


in Bibtex Style

@conference{icaart20,
author={Andreas Sedlmeier and Thomas Gabor and Thomy Phan and Lenz Belzner and Claudia Linnhoff-Popien},
title={Uncertainty-based Out-of-Distribution Classification in Deep Reinforcement Learning},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2020},
pages={522-529},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008949905220529},
isbn={978-989-758-395-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Uncertainty-based Out-of-Distribution Classification in Deep Reinforcement Learning
SN - 978-989-758-395-7
AU - Sedlmeier A.
AU - Gabor T.
AU - Phan T.
AU - Belzner L.
AU - Linnhoff-Popien C.
PY - 2020
SP - 522
EP - 529
DO - 10.5220/0008949905220529