Year: 2019
Type: preprint
Abstract: Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity simulator. Building upon recent research that applies deep reinforcement learning to navigation problems, we present a modular deep reinforcement learning approach to predict the steering angle of the car from raw images. The first module extracts a low-dimensional latent semantic representation of the image. The control module trained with reinforcement learning takes the latent vector as input to predict the correct steering angle. The experimental results have showed that our method is capable of learning to maneuver the car without any human control signals.
Source: arXiv (Cornell University)
Authors: Khan, Qadeer, Schön, Torsten, Wenzel, Patrick
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2932843002