Rlad is a semi-supervised, time series anomaly detection algorithm that uses deep reinforcement learning (DRL) and active learning to efficiently learn and adapt to anomalies in real-world time series data. Our model makes no assumption about the underlying mechanism that produces the observation sequence and continuously adapts the detection model based on experience with anomalous patterns. In addition, it requires no manual tuning of parameters and outperforms all state-of-art methods we compare with, both unsupervised and semi-supervised, across several figures of merit.
We compare Rlad with seven deep-learning based algorithms across two common anomaly detection datasets with up to around 3M data points and between 0.28% to 2.65% anomalies.We outperform all of them across several important performance metrics.
The 7th SIGKDD Workshop on Mining and Learning from Time Series
Rlad: Time Series Anomaly Detection through Reinforcement Learning and Active Learning
@article{wu2021rlad, title={Rlad: Time series anomaly detection through reinforcement learning and active learning}, author={Wu, Tong and Ortiz, Jorge}, journal={arXiv preprint arXiv:2104.00543}, year={2021} }