Author

Ze-Feng Liang

1 paper indexed here

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

IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning

IADD-TR is proposed, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR), which achieves competitive returns with improved sample efficiency on five MuJoCo tasks.

Ze-Feng Liang, Jie Qiao, Rui-Chu Cai et al. · 0 citations