2 papers
cs.LG2025
Explainable reinforcement learning from human feedback to improve alignment
Shicheng Liu, Siyuan Xu, Wenjie Qiu +2
A common and effective strategy for humans to improve an unsatisfactory outcome in daily life is to find a cause of this outcome and correct the cause. In this paper, we investigat…
cs.LG2025
In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates
Shicheng Liu, Minghui Zhu
Inverse reinforcement learning (IRL) aims to learn a reward function and a corresponding policy that best fit the demonstrated trajectories of an expert. However, current IRL works…