A softmax policy network trained on estimated counterfactual rewards reports large estimated clinical improvements on two multimodal datasets.
Optimal policy trees
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Prescriptive Deep Learning
A softmax policy network trained on estimated counterfactual rewards reports large estimated clinical improvements on two multimodal datasets.