huggingface / huggingface/deep-rl-class
[HANDS-ON BUG] Unit 8 part 2, sample-factory 2.1.1 not compatible with pytorch 2.6+
Open
- Dominant language
- MDX
- Stars
- 5k
- Forks
- 811
- PR merge metrics
- No merged PRs in 30d
Description
# Describe the bug
Sample-factory utilizes a pytorch function:
`checkpoint_dict = torch.load(latest_checkpoint, map_location=device)`
Pytorch 2.6+ requires an additional `weights_only=False` variable for the function.
# Material
- [Google Colab](https://colab.research.google.com/github/huggingface/deep-rl-class/blob/main/notebooks/unit8/unit8_part2.ipynb#scrollTo=alxUt7Au-O8e)
# How to Fix
pip install the latest sample-factory:
`!pip install sample-factory==2.1.3`
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.