An incremental rank-lifting algorithm updates winning regions and policies in data-driven stochastic game abstractions by exploiting monotonic growth of under-approximations and shrinkage of over-approximations.
arXiv:2410.06662 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Safety certification of dynamical systems is reformulated as direct classification via kernel embeddings on trajectories, bypassing recursive DP to avoid error compounding and support non-Markovian dynamics.
citing papers explorer
-
Incremental Data-Driven Policy Synthesis via Game Abstractions
An incremental rank-lifting algorithm updates winning regions and policies in data-driven stochastic game abstractions by exploiting monotonic growth of under-approximations and shrinkage of over-approximations.
-
Safety Certification is Classification
Safety certification of dynamical systems is reformulated as direct classification via kernel embeddings on trajectories, bypassing recursive DP to avoid error compounding and support non-Markovian dynamics.