Author

Yinjie Zhong

h-index 0 View on Semantic Scholar

We have 1 of 2 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.

Jul 2026

Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL

This work proposes PRISM, a new multi-reward RL framework built upon the idea of policy-space decomposition and composition, which alleviates the potential conflict during multi-reward policy optimization, while enabling controllability during inference by flexible policy composition.

Ruiming Liang, Yin-Jie Zhong, Yizhen Yuan et al. · arXiv.org · 1 citation