AI RESEARCH
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
arXiv CS.LG
•
ArXi:2605.25604v1 Announce Type: cross Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization, adapting it to real-world multi-reward settings remains challenging. Standard scalarization practices, such as Reward Combination and Advantage Combination, suffer from significant drawbacks: Reward Combination frequently generates advantages with excessively large squared magnitudes that lead to.