Neuroevolution Reinforcement Learning for Inventory Optimization

• PROJECT DESCRIPTION:

  • In this project, we introduce new problem namely Multi-Echelon Inventory Optimization with Delivery Options and Uncertain Discount (MEIO-DO-UD). 

  • As a solution, Neuroevolution Reinforcement Learning (NERL) framework is developed to minimize total system cost.

  • The environment is modeled via System Dynamics (SD) and the actor is presented by integration of Artificial Neural Network and Evolutionary Algorithm (EA), creating an effective decision-making model under dynamic uncertainty. 

  • The experimental study has been conducted where two different supply chain networks are given namely serial and divergence. Three EA algorithms are compared namely Differential Evolution (DE), Memetic Algorithm (MA), and Evolution Strategy (ES). 

• SHARED DATA/PROGRAMS/PAPER:

  • The programs used such as the SD simulation model can be accessed HERE and the journal can be accessed HERE.