Presents hardness results and a sound, conditionally relatively complete verification/synthesis method for entropy objectives in MDPs via convex duality and invariant synthesis, with empirical evaluation on benchmarks.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Entropy Objectives in Markov Decision Processes
Presents hardness results and a sound, conditionally relatively complete verification/synthesis method for entropy objectives in MDPs via convex duality and invariant synthesis, with empirical evaluation on benchmarks.