TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance

arXiv:2509.26627v2 Announce Type: replace Abstract: Designing dense rewards is crucial for reinforcement learning (RL), yet in robotics it often demands extensive manual effort and lacks scalability. One promising solution is to view task progress as a dense reward signal, as it quantifies the degree to which actions advance the system toward task completion over time. We present TimeRewarder, a simple yet effective reward learning method that derives progress estimation signals from passive vid