arXiv AI By Yaswanth Chittepu, Ativ Joshi, Rajarshi Bhattacharjee, Scott Niekum

Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control

Read the original on arXiv AI →

arXiv:2603. 10938v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captures only a single statistic of the cost distribution and fails to account for distributional uncertainty, particularly under heavy tails or rare catastrophic events.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 29

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking

arXiv:2604. 26360v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy.

By Disha Singha