NM-PPG optimizes non-myopic acquisition policies for costly features by enabling pathwise gradients via continuous relaxation and straight-through rollouts in POMDPs, outperforming SOTA baselines.
Optimal control of markov processes with incomplete state information.Journal of Mathematical Analysis and Applications, 10(1):174–205, 1965
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
-
Non-Myopic Active Feature Acquisition via Pathwise Policy Gradients
NM-PPG optimizes non-myopic acquisition policies for costly features by enabling pathwise gradients via continuous relaxation and straight-through rollouts in POMDPs, outperforming SOTA baselines.