Papers / CoRL 2021

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

Mandlekar, Xu, Wong et al. · Stanford / NVIDIA · arXiv:2108.03298

900 citations Read paper Code

A large study of offline learning from proficient and mixed-quality human demonstrations, releasing the robomimic datasets and reproducible baselines.

What this paper connects

Resolving related models, datasets and papers…