/Reinforcement-Learning-VRP

Exploring Reinforcement Learning Solutions to the Vehicle Routing Problem. PPO, A2C, DQN, SAC

Primary LanguageJupyter Notebook

Reinforcement Learning for solving the Vehicle Routing Problem (VRP)

Collaborators:

Research project exploring reinforcement learning solutions to the Vehicle Routing Problem.

Tested Algorithms: PPO, A2C, DQN, SAC

Further Insights Obtained From Europe Cities VRP, OR-Tools, HGS Sample Code, and RL Framework Code

Additional Factors Explored such as Socioeconomic Factors, Environmental Factors, Regulatory Factors, etc in Final Written Report