pytorch / rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Why this job: works in the areas we cover, but does not say which job it does
What it does
TorchRL is a PyTorch-native toolkit for reinforcement learning, decision making, robotics, and simulation. It is not a single algorithm implementation or a narrow benchmark suite: it is a collection of composable pieces for building RL systems while keeping the code close to the PyTorch programming model. Recent work has made this especially strong for recurrent RL, MuJoCo-based control, multi-agent training, replay-buffer and collector infrastructure, and reusable loss/value-estimation components.
Get started
pip install torchrl- Maintenance
- Active
- Last commit yesterday
- Stars
- 3,627
- +8 this week
- Licence
- MIT
- Allows business use
- Downloads for
- 2 systems
- Mac, Linux
- Latest version
- v0.14.1
- Released 30 days ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 20
- Last 90 days
- Issues
- 75% closed
- 238 still open
- Pull requests
- 3,101 merged
- 113 waiting
- Releases
- 37
- 9 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Stable-Baselines-Team / stable-baselines3-contrib | 744 | 14 days ago | MIT | No downloads |
More: download files, languages, topics, project record and preview image
Download files, v0.14.1
- Mac5 files, 41 downloads
- Linux25 files, 292 downloads
Languages
- Python 99%
- Shell <1%
- C++ <1%
- Cuda <1%
Topics
- ai
- control
- decision-making
- distributed-computing
- machine-learning
- marl
- model-based-reinforcement-learning
- multi-agent-reinforcement-learning
- pytorch
- reinforcement-learning
- rl
- robotics
Project record
- JobOther AI tools
- StatusListed
- Commits3,114
- Forks530
- Watching43
- Stars in 28 days+32
- CreatedFeb 1, 2022
- First seen by usNov 7, 2026
- CheckedNov 9, 2026