PiCSRL embeds physics-informed features into reinforcement learning for adaptive sensing, achieving RMSE 0.153 and 98.4% bloom detection on Lake Erie hyperspectral data, outperforming random and UCB baselines.
Data augmentation in high dimensional low sample size setting using a geometry-based variational autoencoder,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning
PiCSRL embeds physics-informed features into reinforcement learning for adaptive sensing, achieving RMSE 0.153 and 98.4% bloom detection on Lake Erie hyperspectral data, outperforming random and UCB baselines.