Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations
This story is from 2026-09-11. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.10866v1 Announce Type: new Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications. Certification methods can improve robustness against advers…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-11 04:00 · arXiv cs.LG
Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations