Introduces RAPCs and a contraction Bellman operator for cost-optimal policies that satisfy probabilistic reach-avoid specifications in stochastic MDPs, with almost-sure convergence to local optima.
Definition B.1(Absorbing Markov Decision Process).The Absorbing Markov Decision Process is defined on f with an added absorbing states
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning
Introduces RAPCs and a contraction Bellman operator for cost-optimal policies that satisfy probabilistic reach-avoid specifications in stochastic MDPs, with almost-sure convergence to local optima.