sled-umich/RACER-augmented_rlbench download history
sled-umich/RACER-augmented_rlbench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 925 times (500 in the last 7 days), and 3,672 times in total. It ranks #20,463 among datasets by monthly downloads.
Rich language-guided failure recovery trajectories augmented from RLbench. We gather the training and validation expert demos from RLbench as $D^{expert}$ (2250 episodes in total), perturb each episode five times and filter unsuccessful trajectories to obtain $D^{recovery+lang}$ (10,159 episodes in