RSL-RL: A Learning Library for Robotics Research
This provides a lightweight and extensible tool for robotics researchers to develop learning-based controllers, but it is incremental as it builds on existing algorithms tailored to robotics.
The authors tackled the need for a specialized reinforcement learning library for robotics by developing RSL-RL, an open-source framework that achieves high-throughput performance in simulation and has been validated in real-world robotic experiments.
RSL-RL is an open-source Reinforcement Learning library tailored to the specific needs of the robotics community. Unlike broad general-purpose frameworks, its design philosophy prioritizes a compact and easily modifiable codebase, allowing researchers to adapt and extend algorithms with minimal overhead. The library focuses on algorithms most widely adopted in robotics, together with auxiliary techniques that address robotics-specific challenges. Optimized for GPU-only training, RSL-RL achieves high-throughput performance in large-scale simulation environments. Its effectiveness has been validated in both simulation benchmarks and in real-world robotic experiments, demonstrating its utility as a lightweight, extensible, and practical framework to develop learning-based robotic controllers. The library is open-sourced at: https://github.com/leggedrobotics/rsl_rl.