arXiv · 2026 · Preprint

SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning

M. Anisimov, Francesco Belardinelli, Matthew Wicker

Date: 2026-04-10
Citations: 0
arXiv: 2604.09452 ↗

Cite

@misc{anisimov2026safeadapt,
  title = {SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning},
  author = {M. Anisimov and Francesco Belardinelli and Matthew Wicker},
  year = {2026},
  eprint = {2604.09452},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.09452},
}