Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
Published in arXiv Preprint, 2026
General-purpose, video-language-input, dense reward model trained on RBM-1M, a large-scale dataset of over 1M trajectories spanning 21 robot embodiments. Significantly improves robot learning across online RL, offline RL, model-based RL, failure detection, and data retrieval for imitation learning.
