huggingface / huggingface/deep-rl-class

[HANDS-ON BUG] Unit 8 part 2, sample-factory 2.1.1 not compatible with pytorch 2.6+

Open
#626 5 comments 0 reactions 0 assignees View on GitHub
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.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.