Welcome to Stable Learning Control documentation

Welcome to the Stable Learning Control (SLC) framework! This framework contains a collection of robust Reinforcement Learning (RL) control algorithms designed to ensure stability. These algorithms are built upon the Lyapunov actor-critic architecture introduced by Han et al. 2020. They guarantee stability and robustness by leveraging Lyapunov stability theory. These algorithms are specifically tailored for use with gymnasium environments that feature a positive definite cost function (i.e. environments in which the cost is minimized). Several ready-to-use compatible environments can be found in the stable-gym and Ros Gazebo Gym packages.

Note

This framework was built upon the SpinningUp educational resource. By doing this, we hope to make it easier for new researchers to start with our Algorithms. If you are new to RL, check out the SpinningUp documentation and play with it before diving into our codebase. Our implementation deviates from the SpinningUp version to increase code maintainability, extensibility, and readability.

Usage

• Installation
  • Install system dependencies
  • Installing Python
  • Installing Stable Learning Control
  • Installing gymnasium environments
• Use with Docker
  • Prerequisites
  • Building the Docker Image
  • Running Experiments
  • Visualizing Experiments
  • Running Other Utilities
  • VSCode Dev Container
• Available Agents
  • Stable Agents
  • Unstable Agents
• Running Experiments
  • Launching from the Command Line
  • Launching from Scripts
• Hyperparameter Tuning
  • Use the ExperimentGrid utility
  • Use the Ray tuning package
• Experiment Outputs
  • Algorithm Outputs
  • Save Directory Location
  • Loading and Running Trained Policies
  • Deploy the saved result onto hardware
• Plotting Results
• Evaluating Robustness
  • Robustness eval configuration file (yaml)
  • Available disturbers
  • Results
  • Use with custom environments
  • How to add new disturber
  • Manual robustness evaluation
• Benchmarks

Utilities

• Loggers
  • Using a Logger
  • Logger Classes
  • Logger helper functions
• MPI Tools
  • Core MPI Utilities
  • MPI + PyTorch Utilities
  • MPI + TensorFlow Utilities
• Run Utils
  • Command Line Interface
  • ExperimentGrid utility
  • Calling Experiments utility
• Plotter
  • Plot utility
• Policy testers
  • Policy eval utility
  • Robustness eval utility

Development

• Contribute to stable-learning-control
  • Contribution guidelines
• Build the documentation
  • Install requirements
  • Build the documentation
  • Deploying
• License

API Documentation

• API Reference
  • stable_learning_control

Etc.

• Acknowledgements

Indices and tables

• Index

• Module Index

• Search Page