|
Download README.md from inouye-lab/StarCraftMotion-checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 1.05 kB
-
https://huggingface.co/inouye-lab/StarCraftMotion-checkpoints/resolve/main/README.md
- Command line
-
hf download hf://inouye-lab/StarCraftMotion-checkpoints/README.md
-
curl -L -o README.md https://huggingface.co/inouye-lab/StarCraftMotion-checkpoints/resolve/main/README.md
1.05 kB
metadata
license: other
license_name: nvidia-source-code-license
license_link: LICENSE
library_name: pytorch
StarCraft Motion checkpoints
HMART weights for StarCraft Motion code and the dataset.
| File | Model |
|---|---|
| hmart.ckpt | HMART |
| hmart_catk.ckpt | HMART + CAT-K |
Simulation tables report mean ± std over three seeds; these weights are from one of them, the run used for the single-run intent and target results.
The motion dictionary and static maps in the code repository are required.
License: NVIDIA Source Code License, non-commercial.
@inproceedings{chen2026starcraftmotion,
title = {{StarCraft Motion}: A Dataset for Agent Simulation in Adversarial and Partially Observable Scenarios},
author = {Yi-Chung Chen and Mingyu Kim and Ruqi Bai and James Zachary Hare and Jing Gao and David I. Inouye},
booktitle = {Advances in Neural Information Processing Systems},
year = {2026}
}