A DQN agent that picks among six anomaly detectors using time series forest rewards achieves high F1 on two electricity datasets, but the evaluation is in-sample.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Unsupervised Anomaly Detection in Electricity Consumption Using Reinforcement Learning and Time Series Forest Based Framework
A DQN agent that picks among six anomaly detectors using time series forest rewards achieves high F1 on two electricity datasets, but the evaluation is in-sample.