Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".
active 2023-08-29 → 2026-08-15 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1083 days from 2023-08-29 to 2026-08-15. Pushes: 238 total, peak 11 in a day. Pull requests: 9 total, peak 2 in a day. Issues: 12 total, peak 3 in a day. Comments: 24 total, peak 3 in a day. Stars: 156 total, peak 3 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 |
|---|---|---|---|---|
| kengz | 258 | 239 | 6 | 7 |
| github-actions[bot] | 7 | 0 | 1 | 6 |
| gleb-kun | 5 | 0 | 1 | 3 |
| joshuamoorexyz | 3 | 0 | 0 | 1 |
| Biggestmeme | 2 | 0 | 0 | 2 |
| hgeisse | 1 | 0 | 0 | 1 |
| jmSNU | 1 | 0 | 0 | 0 |
| radoshi | 1 | 0 | 1 | 0 |
| euribate | 1 | 0 | 0 | 1 |
| byBJ-Park | 1 | 0 | 0 | 1 |
| samanemami | 1 | 0 | 0 | 1 |
| Skyhigh8131 | 1 | 0 | 0 | 0 |
| Trampeltier | 1 | 0 | 0 | 0 |
| HafizRiaz | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Pull request#536radoshi2026-06-20 07:46
- Issue comment#535github-actions[bot]2026-03-20 19:07feat: Phase 5 MuJoCo Playground PPO benchmarks (54 envs)
- Issue comment#534kengz2026-03-20 18:46feat: Phase 5 MuJoCo Playground PPO benchmarks (54 envs)
- Issue comment#510kengz2026-03-04 11:43how to improve the convergence performance of training loss?
- Issue#469kengz2026-03-04 11:42Problem Parsing Input Spec for Enjoy Mode Demo
- Issue comment#533github-actions[bot]2026-03-04 10:41feat: CrossQ algorithm — SAC without target networks
- Issue comment#532github-actions[bot]2026-02-19 03:46feat: TorchArc YAML network architectures
- Pull request#532github-actions[bot]2026-02-19 03:46
- Pull request#532kengz2026-02-19 03:00
- Issue#467kengz2026-02-14 18:38About target entropy in SAC
- Issue comment#467kengz2026-02-14 18:38About target entropy in SAC
- Issue comment#530github-actions[bot]2026-02-11 02:57fix SAC, run benchmarks
- Releasegithub-actions[bot]2026-02-11 02:57v5.0.1
- Pull request#530kengz2026-02-11 02:57
- Pull request#530kengz2026-02-11 02:49
- Issue#516kengz2026-02-02 14:26How to add a custom gym environment in json spec file.
- Issue#520kengz2026-02-02 14:25Docker build failed
- Issue#521kengz2026-02-02 14:24Compatibility to M1 Mac
- Issue comment#500github-actions[bot]2026-02-02 14:07update book branch to v4.2.3 part 2
- Issue comment#502github-actions[bot]2026-02-02 14:07update book branch v4.2.4
- Pull request#528kengz2026-01-31 02:38
- Issue comment#521euribate2025-03-22 22:47Compatibility to M1 Mac
- Issue comment#525gleb-kun2025-03-20 15:24Installation script on Arch Linux does not work correctly
- Issue comment#522joshuamoorexyz2025-02-26 00:11Ubuntu 20.04 no longer works
- Issue#522joshuamoorexyz2025-02-26 00:11Ubuntu 20.04 no longer works
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 156 stars here means stars gained during the window, not the repo's star count.