A new synthesis framework for POMDPs learns finite-state controllers via sampling and model-checking oracles, achieving relative completeness when the policy is regular and solving threshold-safety problems beyond existing formal tools.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning
A new synthesis framework for POMDPs learns finite-state controllers via sampling and model-checking oracles, achieving relative completeness when the policy is regular and solving threshold-safety problems beyond existing formal tools.