SOURCE-LINKED INTELLIGENCE

A Better Spur Should Start From Each Objective

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing traditional linear scalarization to experience severe metric oscillations. To address optimization conflicts among multiple objectives in real-world deployment scenarios, we propose Multi-Marginal Preference Optimization (MMPO), a fine-grained framework that intervenes at the data, gradient, and constraint levels rather than relying on coarse-grained global scalarization. Specifically, MMPO performs exposure debiasing to mitigate sparse and bia

Read original source ↗ Open in workspace

recordType

paper

region

Global