works on
behavioral steering 1composable interventions 1decision making 1policy gradient 1reinforcement learning 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Policy Gradient Steering: Interventions from Behavioral Objectives

Yoann Poupart, Aurélie Beynier, Nicolas Maudet

The paper introduces Policy Gradient Steering (PGS), a reinforcement‑learning based method that uses temporary behavioral objectives to compute removable task vectors for steering…