# Uncertainty-Based Out-of-Distribution Classification in Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2001.00496 · HTML: https://mlsanity.com/paper/2001.00496/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2019.

## Built on by (most cited first, 15 of 15)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Full-Spectrum Out-of-Distribution Detection](https://mlsanity.com/paper/2204.05306/) (2022)
- [Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection](https://mlsanity.com/paper/2404.07099/) (2024)
- [Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.13986/) (2022)
- [Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles](https://mlsanity.com/paper/2207.12380/) (2022)
- [Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation](https://mlsanity.com/paper/2503.05238/) (2025)
- [A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning](https://mlsanity.com/paper/2109.09889/) (2021)
- [Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning](https://mlsanity.com/paper/2106.13703/) (2021)
- [Quantifying Multimodality in World Models](https://mlsanity.com/paper/2112.07263/) (2021)
- [Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning](https://mlsanity.com/paper/2206.14298/) (2022)
- [Uncertainty-based Meta-Reinforcement Learning for Robust Radar Tracking](https://mlsanity.com/paper/2210.14532/) (2022)
- [Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems](https://mlsanity.com/paper/2606.11474/) (2026)
- [MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling](https://mlsanity.com/paper/2210.13545/) (2022)
- [Reliability Quantification of Deep Reinforcement Learning-based Control](https://mlsanity.com/paper/2309.16977/) (2023)
- [DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection](https://mlsanity.com/paper/2510.21638/) (2025)

## Abstract (arXiv)

Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. 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. We further present a first viable solution for calculating a dynamic classification threshold, based on the uncertainty distribution of the training data. 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. In summary, UBOOD presents a viable approach for OOD classification in deep RL settings by leveraging the epistemic uncertainty of the agent's value function.