Skip to content

Releases: Mageed-Ghaleb/MetaForge

MetaForge v1.0.0

08 Jun 06:23
@Mageed-Ghaleb Mageed-Ghaleb
v1.0.0
5f42641

Choose a tag to compare

View all tags
MetaForge v1.0.0 Latest
Latest

🎉 MetaForge v1.0.0 Released!

MetaForge is a modular optimization framework for solving Job Shop Scheduling Problems (JSSP) using a collection of metaheuristics and learning-based algorithms. This release marks the official launch of the project with full support for research, educational, and experimental use.

🚀 Features

✅ Support for benchmark loading in OR-Library format
✅ Modular solver architecture
✅ Core solvers implemented:

  • Tabu Search (ts)
  • Genetic Algorithm (ga)
  • Simulated Annealing (sa)
  • Ant Colony Optimization (aco)
  • Q-Learning (q)
  • Deep Q-Network (Naive) (dqn-naive)
  • Deep Q-Network (Replay Buffer) (dqn-replay)
  • Neuroevolution (neuroevo)

✅ Convergence tracking & plotting
✅ Final Gantt chart visualizations
✅ Benchmark comparison over multiple instances
✅ CSV export of results
✅ Custom metaforge_runner interface for solver integration
✅ Example Jupyter Notebook: notebooks/MetaForge_Example.ipynb

📦 Installation

pip install metaforge

Or clone and install in development mode:

git clone https://github.com/Mageed-Ghaleb/MetaForge.git
cd MetaForge
pip install -e .

📖 Documentation

❤️ Contribute

We welcome feedback, contributions, and new solvers. Star the repo, fork, and submit a PR!

🔗 Repo: MetaForge on GitHub
📬 Contact: mageed.ghaleb@gmail.com

Let's optimize the future!

Assets 2
Loading