Author

Haichao Zhang

Northeastern University

h-index 6 Homepage View on Semantic Scholar

We have 1 of 13 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization (SA-MRPO), which standardizes each reward objective independently and adaptively discounts its contribution according to a batch-level estimate of objective saturation, and dynamically reallocates optimization effort toward under-optimized objectives while empirically maintaining performance on those that are already well satisfied.

Yi-Xuan Wang, Yifei Chen, Haichao Zhang et al. · 0 citations