End-to-End Race Driving with Deep Reinforcement Learning
This work addresses autonomous driving for racing games, showing incremental improvements in reinforcement learning methods for this domain.
The researchers tackled end-to-end race driving using deep reinforcement learning with only RGB camera input, achieving faster convergence and robust driving across varied tracks and conditions, including generalization to unseen tracks and some domain adaptation to real images.
We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding). The newly proposed reward and learning strategies lead together to faster convergence and more robust driving using only RGB image from a forward facing camera. An Asynchronous Actor Critic (A3C) framework is used to learn the car control in a physically and graphically realistic rally game, with the agents evolving simultaneously on tracks with a variety of road structures (turns, hills), graphics (seasons, location) and physics (road adherence). A thorough evaluation is conducted and generalization is proven on unseen tracks and using legal speed limits. Open loop tests on real sequences of images show some domain adaption capability of our method.