On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning

by   Bharat Prakash, et al.

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.


page 2

page 4


Analyzing the Hidden Activations of Deep Policy Networks: Why Representation Matters

We analyze the hidden activations of neural network policies of deep rei...

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

Data-efficient reinforcement learning (RL) in continuous state-action sp...

Transfer and Online Reinforcement Learning in STT-MRAM Based Embedded Systems for Autonomous Drones

In this paper we present an algorithm-hardware codesign for camera-based...

Enhancing the Performance of Multi-Agent Reinforcement Learning for Controlling HVAC Systems

Systems for heating, ventilation and air-conditioning (HVAC) of building...

Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces

While recent advances in deep reinforcement learning have allowed autono...

Quantized Reinforcement Learning (QUARL)

Recent work has shown that quantization can help reduce the memory, comp...

Please sign up or login with your details

Forgot password? Click here to reset