/ppo_paper

PPO Curriculum learning

Primary LanguagePython

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

supported python versions Code style: black Imports: isort dependencies status

🖊 Info

Example render of the environment during evaluation

📚 Setup

Pre-requisites

  • Python >=3.8.0,<3.10
  • Conda

Conda

🤖 Installation

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

🎭 Support and Contributions

Feel free to ask questions. Posting in Github Issues and PRs are also welcome.