Emotional Preferences as Goal-Priority Regulation
Read the original on arXiv AI →The paper investigates whether agents can autonomously set the relative priorities of competing lower-level objectives using emotional preferences generated by higher-level goals, rather than relying on externally defined priorities. It introduces a framework with an inner multi-objective reinforcement learning controller and an outer preference generator that learns state-dependent preference mappings. Experiments in custom multi-objective environments demonstrate that the learned preference function can switch priorities contextually, balance trade-offs, and persist over time, outperforming fixed and handcrafted preference strategies.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.