SKRL: a modular reinforcement learning library with Isaac Gym environments support

Dear community,

I would like to share, in this topic and in a more official way, the RL library (previously mentioned in this post) that we are developing/using in our lab…

skrl is an open-source modular library for Reinforcement Learning written in Python (using PyTorch) and designed with a focus on readability, simplicity, and transparency of algorithm implementation. In addition to supporting the Gym interface, it allows loading and configuring NVIDIA Isaac Gym environments, enabling agents’ simultaneous training by scopes (subsets of environments among all available environments), which may or may not share resources, in the same run."

Please, visit the documentation for usage details and examples

https://skrl.readthedocs.io/en/latest/

Notes:

  • This project is under active continuous development (please make sure you always have the latest version).
  • Bug detection and/or correction, feature requests and everything else are more than welcome :)
  • Please refresh your browser (Ctrl + R) if the API is not displayed correctly in the documentation
7 Likes

Dear community,

skrl version 0.3.0 is now available (it is under active development. Bug detection and/or correction, feature requests and everything else are more than welcome: Open a new issue on GitHub!)

Added:

  • DQN and DDQN agents
  • Export memory to files
  • Postprocessing utility to iterate over memory files
  • Model instantiator utility to allow fast development
  • More examples and contents in the documentation
3 Likes

Hi @toni.sm,

Thanks for sharing your RL library and for the direct support of Isaac Gym environments!

1 Like

Glad to contribute 😁

1 Like

Dear community,

skrl version 0.4.0 is now available (it is under active development. Bug detection and/or correction, feature requests and everything else are more than welcome: Open a new issue on GitHub! ). Please refresh your browser (Ctrl + Shift + R) if the documentation is not displayed correctly

Added

  • CEM, SARSA and Q-learning agents
  • Tabular model
  • Parallel training using multiprocessing
  • Isaac Gym utilities

Changed

  • Initialize agents in a separate method
  • Change the name of the networks argument to models

Fixed

  • Reset environments after post-processing

As part of the Isaac Gym utilities, a lightweight web viewer is available for development without X server

3 Likes