This repository contains an implementation of Proximal Policy Optimization (PPO), a popular reinforcement learning algorithm. PPO is known for its stability and ease of implementation, making it a widely used algorithm in various reinforcement learning tasks, such as gaming, robotics, and more.
In this project, we applied PPO to solve the Lunar Lander environment from OpenAI's Gymnasium.
git clone https://github.com/advafaeian/proximal-policy-optimization.git
cd proximal-policy-optimization
pip install swig
pip install -r requirements.txt
jupyter notebook ppo.ipynb