Autonomous Vehicle Fleet Coordination With Deep Reinforcement Learning

Autonomous vehicles are becoming more common in city transportation. Companies will begin to find a need to teach these vehicles smart city fleet coordination. Currently, simulation based modeling along with hand coded rules dictate the decision making of these autonomous vehicles. We believe that complex intelligent behavior can be learned by these agents through Reinforcement Learning.In this paper, we discuss our work for solving this system by adapting the Deep Q-Learning (DQN) model to the multi-agent setting. Our approach applies deep reinforcement learning by combining convolutional neural networks with DQN to teach agents to fulfill customer demand in an environment that is partially observ-able to them. We also demonstrate how to utilize transfer learning to teach agents to balance multiple objectives such as navigating to a charging station when its en-ergy level is low. The two evaluations presented show that our solution has shown hat we are successfully able to teach agents cooperation policies while balancing multiple objectives.