KBSE learns policies and barrier functions iteratively via conditional mean embeddings to bound unsafe state reachability probabilities during exploration in deep RL.
Annals of Statistics , number = 3, pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.