Welcome to SaferRL!

SaferRL is a Python library that makes it easier to learn about safe reinforcement learning.

Note

This project is under active development.

User Documentation

• Introduction
  • What This Is

Introduction to Safe RL

• Part 1: Key Concepts in Safe RL
  • Why Safe RL?
  • Key Concepts and Terminology

Resources

• Key Papers in Safe RL
  • 1. General Review
  • 2. Model-free RL
  • 3. Model-based RL
  • 4. Transfer Learning
  • 5. Ensemble Learning
  • 6. Human in The Loop
  • 7. Curriculum Learning
  • 8. Risk-sensitive RL
  • 9. Formal Methods
• Benchmarks and Metrics in Safe RL
  • 1. Benchmarks
  • 2. Metrics

Algorithms Docs

• Constrained Policy Optimization
  • Background
  • References

Etc.

• Acknowledgements
• About the Author

Indices and tables

• Index

• Module Index

• Search Page