Self Play
Open
feature request
- Dominant language
- Python
- Stars
- 4.8k
- Forks
- 487
- PR merge metrics
- No merged PRs in 30d
Description
Self play, and generally multi-LM-agent settings are something we are very interested in exploring. What does it take to support this? Does it already work without big overheads?
Contributor guide
Research direction
The issue names no files, tests, or entry points. Start by mapping the existing training and agent-related entry points, then define the required self-play behavior and how support would be verified; the issue is complete only when scope, overhead expectations, and acceptance checks are documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- distributed-systems, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100