no code implementations • 30 Oct 2023 • Jialin Liu, Xinyan Su, Zeyu He, Xiangyu Zhao, Jun Li
In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning.
no code implementations • 30 Oct 2023 • Jialin Liu, Xinyan Su, Peng Zhou, Xiangyu Zhao, Jun Li
Mitigation of the survivor bias is achieved though counterfactual consistency.
no code implementations • 28 Jan 2023 • Xinyan Su, Zhiheng Zhang
In many scenarios, the sum of ITEs of the infected is a more reasonable objective for influence spread, whereas it is difficult to achieve via current IM algorithms.