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.
Maximum Mean Discrepancy Distributionally Robust Nonlinear Chance-Constrained Optimization with Finite-Sample Guarantee , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
KBSE learns policies and barrier functions iteratively via conditional mean embeddings to bound unsafe state reachability probabilities during exploration in deep RL.
citing papers explorer
-
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.
-
Kernel-Based Safe Exploration in Deep Reinforcement Learning
KBSE learns policies and barrier functions iteratively via conditional mean embeddings to bound unsafe state reachability probabilities during exploration in deep RL.