Preprint
Sep 2026
Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation
This work introduces RoboReel: a unified benchmark for evaluating models that learn policies from human videos, and develops four test suites to evaluate the models' performance on multiple axes, including the robustness to visual distractors and the ability to complete long-horizon tasks.
Wei-Wei Gu, Anmol Gupta, Anant Sah et al.
· 1 citation