Welcome to "Simulation of a Supply and Demand System to Define a Winning Company Using AI". This project combines Unity 3D, MLAgents, and advanced AI models to simulate market dynamics and AI-driven decision making.
We devised this project as part as our Bachlor's final year project for Software Engineering at Afeka College of Engineering, Tel-Aviv.
The simulation models a dynamic market with stores, products, and customer behaviors, exploring the effects of supply and demand.
- Stores and Products: Detailed simulation of market entities.
- Customer Behaviors: Algorithms simulating realistic customer actions. (Suggestion: Video clip showing customer interactions in the simulation)
- AI Models: Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) compared.
- Unity 3D Game Engine: For simulation creation.
- MLAgents: Integrating machine learning in the simulation.
- Python and PyTorch: For data analysis and AI model development.
- RNN and LSTM: Employed in AI models for sequential data processing.
The Simulation uses Blender files for the Bus model and thus a Blender installation is needed on your machine in order to read the files. If absent, the simulation will still work but the Bus 3D model will not show.
The provided files are supposed to be 'plug-and-play', meaning you can import them into your desired Unity Hub version and use supposedly any Unity version. We've tested it with quite a few (Post 2021) and they all worked.
We invite you to read the in-depth documentation covering methodologies, AI models, and simulation environment. This is the heart of the project and provides a comprehensive expination of all parts.
This project is released under the following terms:
Attribution-ShareAlike License:
You are free to:
- Share — copy and redistribute the material in any medium or format.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Under the following terms:
- Attribution — You must give appropriate credit to the original authors, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
https://www.linkedin.com/in/deman311/
https://www.linkedin.com/in/timor-bystritskie-4559ab294/
We would like to aknowledge Giorgos Demosthenous 💪🏻 and his amazing youtube video that provided the inspiration for this project.
Thank you for answering our email and questions when we reached out to you and also for and being supportive.
'AI Learns To Dominate A Virtual Market'