Code for the TMLR 2023 paper "PPOCoder: Execution-based Code Generation using Deep Reinforcement Learning"
active 2023-08-15 → 2025-09-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 760 days from 2023-08-15 to 2025-09-12. Pushes: 3 total, peak 3 in a day. Pull requests: 4 total, peak 4 in a day. Issues: 3 total, peak 1 in a day. Comments: 1 total, peak 1 in a day. Stars: 50 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| parshinsh | 7 | 3 | 4 | 0 |
| yiyangchen1 | 2 | 0 | 0 | 0 |
| LOVEISI | 1 | 0 | 0 | 1 |
| AhmedKhaled945 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#17LOVEISI2024-12-10 03:18It looks like rl_run.py is custom for Code Translation, but I want to do a Code Completion task
- Pull request#15parshinsh2024-01-09 21:02
- Pull request#15parshinsh2024-01-09 21:02
- Pull request#14parshinsh2024-01-09 03:48
- Pull request#14parshinsh2024-01-09 03:46
- Issue#12AhmedKhaled9452023-10-01 14:27Pretrained models
- Issue#11yiyangchen12023-09-02 08:56Hello, I noticed that the code snippet "for samp in range(n_syn_samples):" seems to be just multiplying the number of epochs by a factor of n_syn_samples. Is this code segment irrelevant?
- Issue#11yiyangchen12023-08-18 10:57Hello, I noticed that the code snippet "for samp in range(n_syn_samples):" seems to be just multiplying the number of epochs by a factor of n_syn_samples. Is this code segment irrelevant?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 50 stars here means stars gained during the window, not the repo's star count.