Repository Issue Activity (beta)

#724 loading pretrained model with bfloat16 during fine-tuning on 24GB GPU

#285 Robot arm stuttering during action execution with fine-tuned GR00T model

#446 Open-loop evaluation

#745 use_mean_std is plumbed and serialised but never consumed

#771 Negative delta_indices (history frames) silently read from the end of the episode during training

#767 Is test_device_standalone_inference_script_pytorch meant to be gpu-marked?

#760 [REAL_G1 / N1.7] Is there an official Isaac Sim setup and is zero-shot behavior expected?

#761 Training Loss reference & dataset size

#650 Zero-shot deployment of GR00T N1.7 on Unitree G1 + Inspire RH56DFTP hand

#759 G1 reports “robot data late” and develops increasing latency during SONIC teleoperation

#748 install_inference.sh fails due to Isaac-GR00T package-name mismatch

#755 Question: README says select_layer 16 → 12, but GR00T-N1.7-3B ships with 16 — which applies to finetuning?

#750 Request for an official GR00T N1.7 checkpoint for RoboTwin 2.0

#749 Immutable locator for the N1.7 ROBOCASA_GR1_TABLETOP benchmark checkpoint

#747 Does libero/libero_10 out of box checkpoint give good closed loop evaluation results

#742 Padded action dimensions can affect valid predictions in GR00T N1.7

#694 Setup Isaac GROOT Community / Isaac GROOT微信交流群

#450 Deployment on Fourier Gr2 robot，bad result！

#104 Reinforcement learning with GROOT N1

#585 About the effect of language instruction

#297 The open-loop detection effect is very poor

#728 Verify evals on Papers with Code

#723 Can GR00T Learn Suction-Based Grasping Actions (e.g., Vacuum Gripper Control)?

#721 Questions on Hyperparameter Settings.

#715 Data collection for fine-tuning specific tasks.