works on
human feedback 1model predictive control 1preference learning 1safe reinforcement learning 1safety-critical AI 1world models 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.AI2026

Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models

Ilias Kazantzidis, Timothy J. Norman, Yali Du +1

The paper introduces DROPJ, a human‑in‑the‑loop approach that uses preferences and justifications collected from users interacting with a learned world model to train a reward mode…