We reproduce a light RL training framework from OpenAi Five. As seen in the following, the structure of our framework is totally the same as the paper shown. 3 key ingredients in the RL training process, Forward Module, Backward Module, and Env Module are separated.
active 2024-02-13 → 2025-03-04 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 386 days from 2024-02-13 to 2025-03-04. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 2 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Nobody pushed, opened or commented here in the loaded window — this repo's activity is stars and forks only.
Recent activity
Latest issues, pull requests and releases
No issue or PR events — this repo's activity is pushes only.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 2 stars here means stars gained during the window, not the repo's star count.