This repository hosts the ongoing development of a Reinforcement Learning (RL) based actor-critic algorithm aimed at optimizing electric vehicle (EV) charging schedules. The objective is to achieve cost-efficiency and grid stability by intelligently managing when and how EVs are charged.
As the adoption of electric vehicles grows, so does their impact on the electricity grid. By optimizing charging schedules, this project aims to reduce costs for consumers and utility providers while maintaining grid stability. We are leveraging a Reinforcement Learning approach to develop a robust and adaptive charging strategy.
- Actor-Critic Algorithm: The project is built around the actor-critic method, a powerful RL technique that simultaneously learns optimal actions and value functions.
- Ongoing Development: The codebase is under active development, with continuous updates and improvements.
- Cost-Efficiency and Grid Stability: The algorithm focuses on balancing cost-efficiency for users and maintaining the stability of the electricity grid.