DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917040568139776 |
|---|---|
| author | Aljaafari, Tala Kanade, Varun Torr, Philip de Witt, Christian Schroeder |
| author_facet | Aljaafari, Tala Kanade, Varun Torr, Philip de Witt, Christian Schroeder |
| contents | Deploying reinforcement learning (RL) in safety-critical settings is constrained by brittleness under distribution shift. We study out-of-distribution (OOD) detection for RL time series and introduce DEEDEE, a two-statistic detector that revisits representation-heavy pipelines with a minimal alternative. DEEDEE uses only an episodewise mean and an RBF kernel similarity to a training summary, capturing complementary global and local deviations. Despite its simplicity, DEEDEE matches or surpasses contemporary detectors across standard RL OOD suites, delivering a 600-fold reduction in compute (FLOPs / wall-time) and an average 5% absolute accuracy gain over strong baselines. Conceptually, our results indicate that diverse anomaly types often imprint on RL trajectories through a small set of low-order statistics, suggesting a compact foundation for OOD detection in complex environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21638 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection Aljaafari, Tala Kanade, Varun Torr, Philip de Witt, Christian Schroeder Machine Learning Artificial Intelligence Deploying reinforcement learning (RL) in safety-critical settings is constrained by brittleness under distribution shift. We study out-of-distribution (OOD) detection for RL time series and introduce DEEDEE, a two-statistic detector that revisits representation-heavy pipelines with a minimal alternative. DEEDEE uses only an episodewise mean and an RBF kernel similarity to a training summary, capturing complementary global and local deviations. Despite its simplicity, DEEDEE matches or surpasses contemporary detectors across standard RL OOD suites, delivering a 600-fold reduction in compute (FLOPs / wall-time) and an average 5% absolute accuracy gain over strong baselines. Conceptually, our results indicate that diverse anomaly types often imprint on RL trajectories through a small set of low-order statistics, suggesting a compact foundation for OOD detection in complex environments. |
| title | DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.21638 |