works on
Bradley-Terry model 1incomparability 1multi-objective reward modeling 1preference learning 1sample complexity 1

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

collaborators

1 paper

cs.LG2026

Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability

Simone Drago, Marco Mussi, Leonardo Bianconi +1

The paper extends preference‑based reinforcement learning by allowing human experts to label trajectory pairs as incomparable, and introduces a Bradley‑Terry‑inspired rationality m…