UWO

A Unifying Lens on Reward Uncertainty in RLHF

arXiv:2606.09073v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) is bottlenecked by \emph{reward hacking}, where the policy exploits errors in a proxy reward model (RM) and produces high RM scores without genuine quality gains. A natural mitigation is \emph{pessimism}: penalizing rewards in regions where the RM is uncertain. However, standard scalar RMs provide no principled notion of uncertainty.