Extending MONA in Camera Dropbox: Reproduction, Learned Approval, and Design Implications for Reward-Hacking Mitigation
arXiv:2603.29993v1 Announce Type: new
Abstract: Myopic Optimization with Non-myopic Approval (MONA) mitigates multi-step reward hacking by restricting the agent’s planning horizon while supplying far-sighted approval as a training signal~\cite{farquha…