dtPaynt uses SMT-based deductive synthesis with abstraction refinement to find small decision-tree policies for MDPs, outperforming the prior MILP tool OMDT on large models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Small Decision Trees for MDPs with Deductive Synthesis
dtPaynt uses SMT-based deductive synthesis with abstraction refinement to find small decision-tree policies for MDPs, outperforming the prior MILP tool OMDT on large models.