RW-RL Dataset

RW-RL Dataset: Real-World Reinforcement Learning for Robots RW-RL Dataset is a real-world robot interaction dataset released by Boden Intelligence, Junpu Innovation Center, and the MINT Lab at Shanghai Jiao Tong University. It is designed for a bottleneck that imitation-learning-only datasets do not directly solve: how can robot policies keep improving in the physical world after they leave the ideal demonstration trajectory? The broader RW-RL data… See the full description on the dataset page:

Source: Hugging Face Hub (MINT-SJTU/RW-RL-Dataset). Metadata imported from the dataset’s Hub tags.