pith. sign in

On the robustness of safe reinforcement learning under observational perturbations

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 2

years

2026 2

roles

background 1

polarities

background 1

clear filters

representative citing papers

Why Does Agentic Safety Fail to Generalize Across Tasks?

cs.LG · 2026-05-07 · conditional · novelty 6.0

Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.

Safe-RULE: Safe Reinforcement UnLEarning

cs.LG · 2026-06-08 · unverdicted · novelty 5.0

Safe-RULE introduces a reinforcement unlearning defense for offline safe RL that counters data poisoning by removing malicious data influence while preserving task performance and safety.

citing papers explorer

Showing 1 of 1 citing paper after filters.

  • Why Does Agentic Safety Fail to Generalize Across Tasks? cs.LG · 2026-05-07 · conditional · none · ref 69

    Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.