rsl-rl-lib
Fast and simple RL algorithms implemented in PyTorch
Decision gist · record as of 2026-08-14
Yes, if you are doing robotics research with PyTorch and need a lightweight, actively maintained RL training library. The low install friction, permissive license, active maintenance, and zero known vulnerabilities make it a solid choice. Install it if you are working with Isaac Lab, Legged Gym, or similar robot learning environments; otherwise, verify that its algorithm implementations and API match your specific needs.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later; GPU drivers and CUDA toolkit recommended for GPU acceleration, though specific requirements depend on torch installation.
- Low install friction with a pure Python wheel distribution.
- Active maintenance with a recent release (30 days ago) and steady repository activity.
License · maintenance · safety
BSD-3-Clause (permissive) — BSD-3-Clause is a permissive license allowing commercial and private use with minimal restrictions, making the package suitable for both research and production robotics projects.
last release 2026-07-15 (30 days) · last repo commit 2026-07-20 · 2,885 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 369,645 downloads/mo, #7,186 on PyPI
Alternatives
Verify before relying
pip install rsl-rl-lib
from rsl_rl import ... # import desired algorithm or environment interface
# Usage depends on integration with Isaac Lab, Legged Gym, or similar robot learning environment- Whether CPU-only PyTorch is supported or if GPU/CUDA is mandatory
- Specific algorithm implementations available beyond PPO and Student-Teacher Distillation
- API stability and backward compatibility guarantees across releases
What it is and what it does
RSL-RL is a lightweight reinforcement learning library designed specifically for robotics research, built on PyTorch with native GPU acceleration and multi-GPU training support. It provides implementations of common RL algorithms—notably PPO and Student-Teacher Distillation—in a minimal, readable codebase that prioritizes rapid prototyping over the complexity of larger frameworks. The library is used as the training backend for Isaac Lab, Legged Gym, mjlab, and MuJoCo Playground.
The package depends on torch, torchvision, tensordict, numpy, tensorboard, GitPython, onnx, and onnxscript. It requires Python 3.9 or later and is distributed as a pure Python wheel, making installation straightforward. The library is actively maintained (latest release 30 days old, 2885 GitHub stars) and has no known security vulnerabilities.
Use it for
- Training locomotion policies for legged robots using PPO in Isaac Sim or Isaac Gym environments
- Prototyping new RL algorithms without modifying a large framework codebase
- Scaling training across multiple GPUs for faster policy convergence in robotics tasks
- Integrating RL training into existing robot learning pipelines via Isaac Lab or Legged Gym
- Exporting trained policies to ONNX format for deployment on robot hardware
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are doing robotics research with PyTorch and need a lightweight, actively maintained RL training library.
The low install friction, permissive license, active maintenance, and zero known vulnerabilities make it a solid choice. Install it if you are working with Isaac Lab, Legged Gym, or similar robot learning environments; otherwise, verify that its algorithm implementations and API match your specific needs.
Install
rsl-rl-lib on PyPI
Before you install
Low install friction with a pure Python wheel distribution. Active maintenance with a recent release (30 days ago) and steady repository activity. Eight runtime dependencies, primarily PyTorch ecosystem packages, are standard for GPU-accelerated ML work.
Requires Python 3.9 or later; GPU drivers and CUDA toolkit recommended for GPU acceleration, though specific requirements depend on torch installation.
License in practice
BSD-3-Clause is a permissive license allowing commercial and private use with minimal restrictions, making the package suitable for both research and production robotics projects.
Quickstart
pip install rsl-rl-lib
from rsl_rl import ... # import desired algorithm or environment interface
# Usage depends on integration with Isaac Lab, Legged Gym, or similar robot learning environmentVerify before relying
- Whether CPU-only PyTorch is supported or if GPU/CUDA is mandatory
- Specific algorithm implementations available beyond PPO and Student-Teacher Distillation
- API stability and backward compatibility guarantees across releases
Package facts
| License | BSD-3-Clause permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagestorchtorchvisiontensordictnumpytensorboardGitPythononnxonnxscript |
| Maintenance | Actively maintained 30 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 369,645 / month, #7,186 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Operating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: rsl_rl_lib-5.4.2-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “GPU accelerated RL library”
- rsl-rl-libRSL-RL is a GPU-accelerated reinforcement learning library for…
- mjlabmjlab provides a GPU-accelerated reinforcement learning and robotics…
- sglangSGLang is a serving framework that runs large language models and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also skrl · tianshou · verl · dopamine-rl · mjlab · lerobot · torchrl · stable-baselines3 · sb3-contrib · mabwiser