This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function. A Deep Q-Network agent was trained in a simulated environment to handle speed and lane change decisions for a truck-trailer combination. In a highway driving case, it is shown that the method produced an agent that matched or surpassed the performance of a commonly used reference model. To demonstrate the generality of the method, the exact same algorithm was also tested by training it for an overtaking case on a road with oncoming traffic. Furthermore, a novel way of applying a convolutional neural network to high level input that represents interchangeable objects is also introduced.
@article{arxiv.1803.10056,
title = {Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning},
author = {Carl-Johan Hoel and Krister Wolff and Leo Laine},
journal= {arXiv preprint arXiv:1803.10056},
year = {2019}
}