We view intersection handling on autonomous vehicles as a reinforcement learning problem, and study its behavior in a transfer learning setting. We show that a network trained on one type of intersection generally is not able to generalize to other intersections. However, a network that is pre-trained on one intersection and fine-tuned on another performs better on the new task compared to training in isolation. This network also retains knowledge of the prior task, even though some forgetting occurs. Finally, we show that the benefits of fine-tuning hold when transferring simulated intersection handling knowledge to a real autonomous vehicle.
@article{arxiv.1712.01106,
title = {Transferring Autonomous Driving Knowledge on Simulated and Real Intersections},
author = {David Isele and Akansel Cosgun},
journal= {arXiv preprint arXiv:1712.01106},
year = {2017}
}
Comments
Appeared in Lifelong Learning Workshop @ ICML 2017. arXiv admin note: text overlap with arXiv:1705.01197