pith. machine review for the scientific record. sign in

Neural Computation , volume =

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

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

Interpreting Reinforcement Learning Agents with Susceptibilities

cs.LG · 2026-05-08 · unverdicted · novelty 7.0

Susceptibilities applied to regret in deep RL agents reveal stagewise internal development in parameter space of a gridworld model that policy inspection alone cannot detect, validated via activation steering.

citing papers explorer

Showing 2 of 2 citing papers.