SKRL - Reinforcement Learning library (1.0.0)#

skrl is an open-source library for Reinforcement Learning written in Python (on top of PyTorch and JAX) and designed with a focus on modularity, readability, simplicity and transparency of algorithm implementation. In addition to supporting the OpenAI Gym / Farama Gymnasium, DeepMind and other environment interfaces, it allows loading and configuring NVIDIA Isaac Gym, NVIDIA Isaac Orbit and NVIDIA Omniverse 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.

Main features:

PyTorch ( ) and JAX ( )
Clean code
Modularity and reusability
Documented library, code and implementations
Support for Gym/Gymnasium (single and vectorized), DeepMind, NVIDIA Isaac Gym (preview 2, 3 and 4), NVIDIA Isaac Orbit, NVIDIA Omniverse Isaac Gym environments, among others
Simultaneous learning by scopes in Gym/Gymnasium (vectorized), NVIDIA Isaac Gym, NVIDIA Isaac Orbit and NVIDIA Omniverse Isaac Gym

Warning

skrl is under active continuous development. Make sure you always have the latest version. Visit the develop branch or its documentation to access the latest updates to be released.

GitHub repository: https://github.com/Toni-SM/skrl
Questions or discussions: https://github.com/Toni-SM/skrl/discussions

Citing skrl: To cite this library (created at Mondragon Unibertsitatea) use the following reference to its article: skrl: Modular and Flexible Library for Reinforcement Learning.

@article{serrano2023skrl,
  author  = {Antonio Serrano-Muñoz and Dimitrios Chrysostomou and Simon Bøgh and Nestor Arana-Arexolaleiba},
  title   = {skrl: Modular and Flexible Library for Reinforcement Learning},
  journal = {Journal of Machine Learning Research},
  year    = {2023},
  volume  = {24},
  number  = {254},
  pages   = {1--9},
  url     = {http://jmlr.org/papers/v24/23-0112.html}
}

User guide#

To start using the library, visit the following links:

Library components (overview)#

Agents#

Definition of reinforcement learning algorithms that compute an optimal policy. All agents inherit from one and only one base class (that defines a uniform interface and provides for common functionalities) but which is not tied to the implementation details of the algorithms

Advantage Actor Critic (A2C)

Adversarial Motion Priors (AMP)

Cross-Entropy Method (CEM)

Deep Deterministic Policy Gradient (DDPG)

Double Deep Q-Network (DDQN)

Deep Q-Network (DQN)

Proximal Policy Optimization (PPO)

Q-learning (Q-learning)

Robust Policy Optimization (RPO)

Soft Actor-Critic (SAC)

State Action Reward State Action (SARSA)

Twin-Delayed DDPG (TD3)

Trust Region Policy Optimization (TRPO)

Multi-agents#

Definition of reinforcement learning algorithms that compute an optimal policies. All agents (multi-agents) inherit from one and only one base class (that defines a uniform interface and provides for common functionalities) but which is not tied to the implementation details of the algorithms

Independent Proximal Policy Optimization (IPPO)

Multi-Agent Proximal Policy Optimization (MAPPO)

Environments#

Definition of the Isaac Gym (preview 2, 3 and 4), Isaac Orbit and Omniverse Isaac Gym environment loaders, and wrappers for the Gym/Gymnasium, DeepMind, Isaac Gym, Isaac Orbit, Omniverse Isaac Gym environments, among others

Single-agent environment wrapping for Gym/Gymnasium, DeepMind, Isaac Gym, Isaac Orbit, Omniverse Isaac Gym environments, among others

Multi-agent environment wrapping for PettingZoo and Bi-DexHands environments

Loading Isaac Gym environments

Loading Isaac Orbit environments

Loading Omniverse Isaac Gym environments

Memories#

Generic memory definitions. Such memories are not bound to any agent and can be used for any role such as rollout buffer or experience replay memory, for example. All memories inherit from a base class that defines a uniform interface and keeps track (in allocated tensors) of transitions with the environment or other defined data

Random memory

Models#

Definition of helper mixins for the construction of tabular functions or function approximators using artificial neural networks. This library does not provide predefined policies but helper mixins to create discrete and continuous (stochastic or deterministic) policies in which the user only has to define the tables (tensors) or artificial neural networks. All models inherit from one base class that defines a uniform interface and provides for common functionalities. In addition, it is possible to create shared model by combining the implemented definitions

Tabular model (discrete domain)

Categorical model (discrete domain)

Gaussian model (continuous domain)

Multivariate Gaussian model (continuous domain)

Deterministic model (continuous domain)

Trainers#

Definition of the procedures responsible for managing the agent’s training and interaction with the environment. All trainers inherit from a base class that defines a uniform interface and provides for common functionalities

Sequential trainer

Parallel trainer

Manual trainer

Resources#

Definition of resources used by the agents during training and/or evaluation, such as exploration noises or learning rate schedulers

Noises: Definition of the noises used by the agents during the exploration stage. All noises inherit from a base class that defines a uniform interface

Gaussian noise

Ornstein-Uhlenbeck noise

Learning rate schedulers: Definition of learning rate schedulers. All schedulers inherit from the PyTorch _LRScheduler class (see how to adjust learning rate in the PyTorch documentation for more details)

KL Adaptive

Preprocessors: Definition of preprocessors

Running standard scaler

Optimizers: Definition of optimizers

Adam

Utils and configurations#

Definition of utilities and configurations

ML frameworks configuration

Random seed

Memory and Tensorboard file post-processing

Model instantiators

Hugging Face integration

Isaac Gym utils

Omniverse Isaac Gym utils