Welcome to ReleZoo’s documentation!
ReleZoo is a Python library/SDK to run and develop Reinforcement Learning (RL) algorithms.
It is basically an opinionated abstraction of the several aspects RL experimentation might have (environments, parallel environments, logging, training loop, evaluation, e.t.c.) to make easier to run, visualize, and try out new experiments. I developed this as a way to help me learn about RL coming from a more traditional SWE background. Basically I intend this project to be my own version of Stable_baselines3.
Check out the Basic section for further information, including how to Installation the project.
Note
This project is under active development.
Contents
Usage
Architecture
Algorithms
Utils
Wandb Reports