Analyzing Knowledge Transfer in Deep Q-Networks for Autonomously Handling Multiple Intersections
Abstract
We analyze how the knowledge to autonomously handle one type of intersection, represented as a Deep Q-Network, translates to other types of intersections (tasks). We view intersection handling as a deep reinforcement learning problem, which approximates the state action Q function as a deep neural network. Using a traffic simulator, we show that directly copying a network trained for one type of intersection to another type of intersection decreases the success rate. We also show that when a network that is pre-trained on Task A and then is fine-tuned on a Task B, the resulting network not only performs better on the Task B than an network exclusively trained on Task A, but also retained knowledge on the Task A. Finally, we examine a lifelong learning setting, where we train a single network on five different types of intersections sequentially and show that the resulting network exhibited catastrophic forgetting of knowledge on previous tasks. This result suggests a need for a long-term memory component to preserve knowledge.
Cite
@article{arxiv.1705.01197,
title = {Analyzing Knowledge Transfer in Deep Q-Networks for Autonomously Handling Multiple Intersections},
author = {David Isele and Akansel Cosgun and Kikuo Fujimura},
journal= {arXiv preprint arXiv:1705.01197},
year = {2017}
}
Comments
Submitted to IEEE International Conference on Intelligent Transportation Systems (ITSC 2017)