google-deepmind / google-deepmind/meltingpot
Request: Support for vectorised environments
Open
- Dominant language
- Python
- Stars
- 873
- Forks
- 162
- Avg merge
- 3d 12h
- Merged PRs (30d)
- 29
Description
Hi All
Is it possible to run MeltingPot with vectorised environments? I am using CleanRL + Shimmy to run MeltingPot but when I try to use `concat_vec_envs_v1` I get error: 'TypeError: cannot pickle `dmlab2d.dmlab2d_pybind.Lab2d object`. Is there any other way? Any advice would be appreciated.
Contributor guide
Assessment
This issue has not been assessed yet.