The authors introduce the first sound stopping criterion for value iteration on concurrent stochastic games, using recursively deflated over-approximations to certify epsilon-precision.
Verification of Markov decision processes using learning algorithms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Stopping Criteria for Value Iteration on Concurrent Stochastic Reachability and Safety Games
The authors introduce the first sound stopping criterion for value iteration on concurrent stochastic games, using recursively deflated over-approximations to certify epsilon-precision.