guest@minsoo.blog:~/projects$ cd PPO-scratch
  
  guest@minsoo.blog:~/projects/PPO-scratch$ cat README.md

PPO-scratch

Github link    

Description

• A complete implementation of the Proximal Policy Optimization (PPO) algorithm from scratch, compatible with OpenAI Gym/Gymnasium API.

Features

• Gymnasium Compatible: Compatible with any Gymnasium environment (discrete or continuous)
• Training Utilities: Includes training scripts with progress tracking and visualization
• Model Persistence: Save and load trained models with automatic compatibility checking

Tech Stack

• ML framework: pytorch, gymnasium