Introduces SAT with isotopic state lumping to estimate two variance-based risks in MDPs with stochastic transition rewards and randomized policies.
Robust control of Markov decision processes with uncertain transition matrices,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping
Introduces SAT with isotopic state lumping to estimate two variance-based risks in MDPs with stochastic transition rewards and randomized policies.