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.
2025 (to appear, preprint at https://arxiv.org/abs/2404.05424)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Shielding the policy improvement process in offline RL yields policies that are safe with high probability while outperforming unshielded baselines in both average and worst-case performance, especially under limited data.
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.
-
Robust Probabilistic Shielding for Safe Offline Reinforcement Learning
Shielding the policy improvement process in offline RL yields policies that are safe with high probability while outperforming unshielded baselines in both average and worst-case performance, especially under limited data.