google-deepmind / google-deepmind/lab
Is Deepmind Lab support for multi agent to play in one environment.
Open
- Dominant language
- C
- Stars
- 7.4k
- Forks
- 1.4k
- PR merge metrics
- No merged PRs in 30d
Description
Currently I can train agent against build-in AI in DeepMind Lab, but I don't know how to put multi agents in same environment. It seems to support that according to the Paper (Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
). How should I change the code to make training multi agents available? Does anyone know that?
Contributor guide
Assessment
This issue has not been assessed yet.