Solving a Real-world optimization problem using Proximal Policy Optimization combined with Curriculum Learning and Reward Engineering ♻️

🖊 Info

Example render of the environment during evaluation

📚 Setup

Pre-requisites

• Python >=3.8.0,<3.10
• Conda

Conda

• Follow instructions : Installer link

🤖 Installation

git clone git@gitlab.com:anonymousppocl1/ppo_paper.git
cd ppo_paper

Create a conda virtual environment and run the following commands

conda create -n myenv python=3.8.8
conda activate myenv
pip install -r requirements.txt

📊 Reproduce results from the paper

python reproduce_results_paper.py