Yejin Choi

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

GDPO：多奖励强化学习优化中的组奖励解耦归一化策略优化

Shih-Yang Liu, Xin Dong, Ximing Lu, Shizhe Diao, Peter Belcak, Mingjie Liu, Min-Hung Chen, Hongxu Yin, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Yejin Choi, Jan Kautz, Pavlo Molchanov

机构 * NVIDIA 纠错

AI总结 GDPO通过解耦奖励归一化提升多奖励强化学习优化的稳定性和准确性，优于GRPO。

Comments NVIDIA-Tech Report