pytorch/rl
An official PyTorch library for reinforcement learning with modular primitives for training RL agents.
Not currently ranked — collecting fresh signals.
star history
TorchRL is a Python-first reinforcement learning library built on PyTorch. It provides modular, composable primitives for building and training RL algorithms including support for multi-agent and model-based RL. The library targets researchers and practitioners working on decision-making systems in robotics and control environments.
Frequently asked
- What is pytorch/rl?
- An official PyTorch library for reinforcement learning with modular primitives for training RL agents.
- Is rl open source?
- Yes — pytorch/rl is open source, released under the MIT license.
- What language is rl written in?
- pytorch/rl is primarily written in Python.
- How popular is rl?
- pytorch/rl has 3.5k stars on GitHub.
- Where can I find rl?
- pytorch/rl is on GitHub at https://github.com/pytorch/rl.