Welcome to GBRL’s documentation!

GBRL is a Python-based Gradient Boosting Trees (GBT) library, similar to popular packages such as XGBoost , CatBoost , but specifically designed and optimized for reinforcement learning (RL). GBRL is implemented in C++/CUDA aimed to seamlessly integrate within popular RL libraries.

User Guide:

• Quickstart
  • Prerequisites
  • Installation
  • Dependencies
• Examples
  • Basic Usage: Training, Saving, Loading, Copying
  • RL using GBRL
  • Explainability

Documentation:

• GBRL Module
  • GBRL
• Actor Critic Module
  • ActorCritic Class
  • ParametricActor Class
  • GaussianActor Class
  • ContinuousCritic Class
  • DiscreteCritic Class

Indices and tables

• Index

• Module Index

• Search Page