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.
AAAI 10(315149.315395) (1999)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A sound reward-shaping mechanism generates belief-dependent rewards from certified LTL satisfaction and integrates it into Monte Carlo planning for POMDPs with temporal logic objectives.
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.
-
Ensuring Logic in the Fog: Sound POMDP Synthesis with LTL Objectives
A sound reward-shaping mechanism generates belief-dependent rewards from certified LTL satisfaction and integrates it into Monte Carlo planning for POMDPs with temporal logic objectives.