A decision-tree behavior cloning approach that chooses the most frequent treatments per patient state yields interpretable policies with reliable off-policy evaluation in two clinical datasets.
Following (Matsson et al., 2024a), we restricted the analysis to classes of DMARDs rather than individ- ual drugs
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
-
Pragmatic Policy Development via Interpretable Behavior Cloning
A decision-tree behavior cloning approach that chooses the most frequent treatments per patient state yields interpretable policies with reliable off-policy evaluation in two clinical datasets.