Code implementation for the paper "Multi-Agent Learning of Efficient Fulfilment and Routing Strategies in E-Commerce" The code contains
- Environment : Responsible for rules and returns rewards and panalty for the learning model.
- C2S Agent : Which Assigns customer to a warehouse using Markov's Decision Process
- VRP : The agent decided the route for customer
- GAE : Graphical Auto Encoder, to get the state space for the RL.