Downloads · 30 days
12
20% of all-time downloads
aryannzzz/act-metaworld-shelf-standard
act-metaworld-shelf-standard is a robotics model from aryannzzz. Use it for the robotics task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Action Chunking Transformer for MetaWorld Shelf-Place-v3 Task
Downloads · 30 days
12
20% of all-time downloads
All-time downloads
60
Public
Repo size
968 MB
Likes
0
Public
Click a slice to open those files.
.pth743 MB · 77%
From the Hugging Face model README
Action Chunking Transformer for MetaWorld Shelf-Place-v3 Task
This is a STANDARD ACT model trained on the MetaWorld shelf-place-v3 task.
⚠️ Known Issue: This model achieves 0% success in evaluation despite low training loss.
Root Cause: Training data collected from fixed initial state → model learned specific scenario perfectly but cannot generalize to randomized evaluation states.
Solution: Requires diverse demonstration data with varied initial states.
| Model | Val Loss | Improvement |
|---|---|---|
| Standard ACT | 0.1289 | baseline |
| Modified ACT | 0.0931 | 27.8% better |
import torch
from huggingface_hub import hf_hub_download
# Download checkpoint
checkpoint_path = hf_hub_download(
repo_id="aryannzzz/act-metaworld-shelf-standard",
filename="best_model.pth"
)
# Load model
checkpoint = torch.load(checkpoint_path, weights_only=False)
# model.load_state_dict(checkpoint['model_state_dict'])
best_model.pth: Model checkpoint (contains model_state_dict, optimizer_state_dict, and training stats)norm_stats.npz: Normalization statistics (state_mean, state_std, action_mean, action_std)config.json: Model configurationBased on "Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware" (Zhao et al., RSS 2023)
@article{zhao2023learning,
title={Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware},
author={Zhao, Tony Z and others},
journal={RSS},
year={2023}
}
MIT
For questions or issues, please open an issue in the repository.