leggedrobotics/rsl_rl

A fast and simple implementation of learning algorithms for robotics.

What it solves

RSL-RL provides a lightweight, GPU-accelerated learning library specifically for robotics research. It eliminates the overhead associated with large, complex libraries, allowing researchers to prototype and test new ideas quickly.

How it works

It is a compact codebase designed for high-throughput training and rapid prototyping. It includes native multi-GPU support and implements common robot learning algorithms, such as Proximal Policy Optimization (PPO) and Student-Teacher Distillation.

Who it’s for

Robotics researchers who need a flexible, and high-performance framework for training robot behaviors.

Highlights

  • GPU Acceleration: Optimized for high-throughput training with multi-GPU support.
  • Minimal Codebase: Designed to be readable and extensible for easy modification.
  • Robotics-First Methods: Includes specialized algorithms like PPO and Student-Teacher Distillation.
  • Broad Integration: Used by major environments like Isaac Lab, Legged Gym, and MuJoCo Playground.

Related

  • Project
    rl-tools/rl-tools

    A fast, portable C++ library for deep reinforcement learning and continuous control, optimized for everything from microcontrollers to GPUs.

  • Project
    NVIDIA/cuml

    A GPU-accelerated machine learning library that provides scikit-learn-style APIs and a transparent acceleration module to speed up ML workloads on NVIDIA GPUs.

  • Project
    alibaba/ROLL

    An efficient scaling library for reinforcement learning with LLMs that optimizes training and inference across large GPU clusters using a distributed Ray-based architecture.

  • Project
    isaac-sim/IsaacLab

    A GPU-accelerated open-source framework built on NVIDIA Isaac Sim for simplifying robotics research in reinforcement learning, imitation learning, and motion planning.

  • Project
    uxlfoundation/oneDAL

    A C++ and DPC++ library that provides hardware-accelerated machine learning routines for tabular data across CPUs, GPUs, and distributed systems.