Ruishuo Chen, Xun Wang, Rui Hu, Zhuoran Li, and Longbo Huang
In submission , 2025. [PDF]
TD-GFN: a proxy-free framework for training GFlowNets from offline data, achieving superior efficiency and performance without out-of-dataset reward queries.
Ruishuo Chen*, Wutong Lu*, Qi Hao, Yifan Meng, Pengfei Chen, and Chenxi Shi
In submission , 2025. [PDF] [Code]
DSARD: An automated unsupervised method for solar active region detection in SDO/HMI magnetograms.
Zhuoran Li, Ruishuo Chen, Hai Zhong, and Longbo Huang
In submission , 2025. [PDF]
SOCD: An offline reinforcement learning algorithm for multi-user delay-constrained scheduling.
Tian Xu*, Zhilong Zhang*, Ruishuo Chen, Yihao Sun, and Yang Yu
The Thirty-eighth Annual Conference on Neural Information Processing Systems [NeurIPS], 2024. [PDF] [Code]
OPT-AIL: First provably efficient adversarial imitation learning with general function approximation, achieving SOTA performance through simplified optimization.