skrl: Modular and Flexible Library for Reinforcement Learning
This provides a modular tool for researchers and practitioners in reinforcement learning, though it is incremental as it builds on existing libraries and interfaces.
The authors tackled the need for a more readable and flexible reinforcement learning library by developing skrl, an open-source Python library that supports various environment interfaces and enables simultaneous training of multiple agents with customizable scopes.
skrl is an open-source modular library for reinforcement learning written in Python and designed with a focus on readability, simplicity, and transparency of algorithm implementations. In addition to supporting environments that use the traditional interfaces from OpenAI Gym and DeepMind, it provides the facility to load, configure, and operate NVIDIA Isaac Gym and NVIDIA Omniverse Isaac Gym environments. Furthermore, it enables the simultaneous training of several agents with customizable scopes (subsets of environments among all available ones), which may or may not share resources, in the same run. The library's documentation can be found at https://skrl.readthedocs.io and its source code is available on GitHub at https://github.com/Toni-SM/skrl.