On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning
Loading...
Links to Files
Permanent Link
Author/Creator ORCID
Date
2019-03-25
Type of Work
Department
Program
Citation of Original Publication
Bharat Prakash, Mark Horton, et.al, On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning, Computer Science, Machine Learning, https://arxiv.org/pdf/1903.10404.pdf
Rights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Abstract
In autonomous embedded systems, it is often vital to reduce the
amount of actions taken in the real world and energy required to
learn a policy. Training reinforcement learning agents from high
dimensional image representations can be very expensive and time
consuming. Autoencoders are deep neural network used to compress
high dimensional data such as pixelated images into small
latent representations. This compression model is vital to efficiently
learn policies, especially when learning on embedded systems. We
have implemented this model on the NVIDIA Jetson TX2 embedded
GPU, and evaluated the power consumption, throughput, and energy
consumption of the autoencoders for various CPU/GPU core
combinations, frequencies, and model parameters. Additionally, we
have shown the reconstructions generated by the autoencoder to
analyze the quality of the generated compressed representation and
also the performance of the reinforcement learning agent. Finally,
we have presented an assessment of the viability of training these
models on embedded systems and their usefulness in developing autonomous
policies. Using autoencoders, we were able to achieve 4-5
× improved performance compared to a baseline RL agent with a
convolutional feature extractor, while using less than 2W of power.