Python · MIT
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
★ 3.6k
Stars
528 forks · 348 open issues
+1.0/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
31.1
Momentum / 100
see the breakdown below
4y ago
Created
last push 3d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 5.8 | +1.0/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.87× the monthly pace |
| Freshness | 15 | 15.0 | last push 3d ago; decays to zero at 180 days |
| Scale | 15 | 10.3 | 3.6k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 31.1 | sum of the above |
Detail
| Topics | aicontroldecision-makingdistributed-computingmachine-learningmarlmodel-based-reinforcement-learningmulti-agent-reinforcement-learningpytorchreinforcement-learningrlroboticstorch |
| Matched on | Robotics (robotics) |
| Short window | +7 stars over 7 days = 1.0/day |
| Long window | +30 stars over 26 days = 1.2/day |
| Lifetime average | 2.09 stars/day over 1,738 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |