With data accessible such as the roads, fuel level, traffic information and gas prices, the goal of this paper is to investigate how reinforcement learning can be used to plan an optimal strategy of where and when for a driver to refuel gas. This whole decision making process will modelled through a Markov Decision Process. In this paper, model simulations will be used instead of real data due to the time frame, and to provide a proof of concept that can be explored further.
With data accessible such as the roads, fuel level, traffic information and gas prices, the goal of this paper is to investigate how reinforcement learning can be used to plan an optimal strategy of where and when for a driver to refuel gas. This whole decision making process will modelled through a Markov Decision Process. In this paper, model simulations will be used instead of real data due to the time frame, and to provide a proof of concept that can be explored further.