A reinforcement learning approach learns an adaptive acquisition function for active learning by bootstrapping from a heuristic and training a policy network on feedback from labeling rounds.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Active Learning with Adaptive Acquisition
A reinforcement learning approach learns an adaptive acquisition function for active learning by bootstrapping from a heuristic and training a policy network on feedback from labeling rounds.