Accelerating the training of deep reinforcement learning in autonomous driving
Abstract
Deep reinforcement learning has been successful in solving common autonomous driving tasks such as lane-keeping by simply using pixel data from the front view camera as input. However, raw pixel data contains a very high-dimensional observation that affects the learning quality of the agent due to the complexity imposed by a 'realistic' urban environment. Ergo, we investigate how compressing the raw pixel data from high-dimensional state to low-dimensional latent space offline using a variational autoencoder can significantly improve the training of a deep reinforcement learning agent. We evaluated our method on a simulated autonomous vehicle in car learning to act and compared our results with many baselines including deep deterministic policy gradient, proximal policy optimization, and soft actorcritic. The result shows that the method greatly accelerates the training time and there was a remarkable improvement in the quality of the deep reinforcement learning agent.
Keywords
Autonomous driving; Deep reinforcement learning; Latent state representation; Variational autoencoder
Full Text:
PDFDOI: http://doi.org/10.11591/ijai.v10.i3.pp649-656
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
IAES International Journal of Artificial Intelligence (IJ-AI)
ISSN/e-ISSN 2089-4872/2252-8938
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).