pith. sign in

For step sizesη < 2g/LQ, the improvement is positive

Substituting∆a=η∇ aQ/∥∇aQ∥2: Q(s, a+ ∆a)−Q(s, a)≥ ∇ aQ⊤∆a− LQη2 2 =η∥∇ aQ∥2 − LQη2 2 When∇ aQ̸= 0, letg=∥∇ aQ∥2 >0

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.RO 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

TAIL-Safe: Task-Agnostic Safety Monitoring for Imitation Learning Policies

cs.RO · 2026-05-02 · unverdicted · novelty 5.0 · 2 refs

TAIL-Safe learns a Lipschitz Q-function from visibility, recognizability, and graspability criteria in a Gaussian Splatting twin to define an empirical safe set for IL policies and recovers unsafe actions via Nagumo-inspired gradient ascent.

citing papers explorer

Showing 1 of 1 citing paper.

  • TAIL-Safe: Task-Agnostic Safety Monitoring for Imitation Learning Policies cs.RO · 2026-05-02 · unverdicted · none · ref 30 · 2 links

    TAIL-Safe learns a Lipschitz Q-function from visibility, recognizability, and graspability criteria in a Gaussian Splatting twin to define an empirical safe set for IL policies and recovers unsafe actions via Nagumo-inspired gradient ascent.