4 releases (breaking)

0.4.0 Jun 19, 2024
0.3.0 Jun 4, 2024
0.2.0 Apr 21, 2024
0.1.0 Apr 20, 2024

#356 in Machine learning

MIT license

97KB
2.5K SLoC

rl - A rust reinforcement learning library

Current Crates.io Version

About

rl is a fully rust-native reinforcement learning library with the goal of providing a unified RL development experience, including:

  • High-performance production-ready implementations of all SoTA RL algorithms powered by the rust-native deep learning framework burn
  • Out of the box benchmarking multiple algorithms against eachother
  • Detailed logging and training visualization
  • Maximum extensibility for creating and testing new experimental algorithms
  • Gym environments
  • A comfortable learning experience for those new to RL
  • General RL peripherals and utility functions

Dependencies

~39–79MB
~1.5M SLoC