• Home
  • Search
  • Knowledge Transfer for On-Device Deep Reinforcement Learning in Resource Constrained Edge Computing Systems
  • Cite Icon41
  • https://doi.org/10.1109/access.2020.3014922Copy DOI Icon

Knowledge Transfer for On-Device Deep Reinforcement Learning in Resource Constrained Edge Computing Systems

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep reinforcement learning (DRL) is a promising approach for developing control policies by learning how to perform tasks. Edge devices are required to control their actions by exploiting DRL to solve tasks autonomously in various applications such as smart manufacturing and autonomous driving. However, the resource limitations of edge devices make it unfeasible for them to train their policies from scratch. It is also impractical for such an edge device to use the policy with a large number of layers and parameters, which is pre-trained by a centralized cloud infrastructure with high computational power. In this paper, we propose a method, on-device DRL with distillation (OD3), to efficiently transfer distilled knowledge of how to behave for on-device DRL in resource-constrained edge computing systems. Our proposed method makes it possible to simultaneously perform knowledge transfer and policy model compression in a single training process on edge devices with considering their limited resource budgets. The novelty of our method is to apply a knowledge distillation approach to DRL based edge device control in integrated edge cloud environments. We analyze the performance of the proposed method by implementing it on a commercial embedded system-on-module equipped with limited hardware resources. The experimental results show that 1) edge policy training with the proposed method achieves near-cloud-performance in terms of average rewards, although the size of the edge policy network is significantly smaller compared to that of the cloud policy network and 2) the training time elapsed for edge policy training with our method is reduced significantly compared to edge policy training from scratch.

Loading PDF

Similar Papers
  • Research Article
  • Citations124

Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle

  • Jan 01, 2020
  • IEEE Access
  • Qilei Zhang +4
  • Research Article
  • Citations15

Federated learning by employing knowledge distillation on edge devices with limited hardware resources

  • Feb 14, 2023
  • Neurocomputing
  • Ehsan Tanghatari +3
  • PDF
  • Research Article
  • Citations11

Image Processing for Smart Agriculture Applications Using Cloud-Fog Computing

  • Sep 14, 2024
  • Sensors (Basel, Switzerland)
  • Dušan Marković +3
  • Research Article
  • Citations104

A3C-DO: A Regional Resource Scheduling Framework Based on Deep Reinforcement Learning in Edge Scenario

  • Apr 17, 2020
  • IEEE Transactions on Computers
  • Junfeng Zou +3
  • Research Article
  • Citations4

Anti‐Attack Scheme for Edge Devices Based on Deep Reinforcement Learning

  • Jan 01, 2021
  • Wireless Communications and Mobile Computing
  • Rui Zhang +4
  • Book Chapter
  • Citations8

Deep Model Compression via Two-Stage Deep Reinforcement Learning

  • Jan 01, 2021
  • Huixin Zhan +2
  • Conference Article
  • Citations5

Continuous Control for Autonomous Underwater Vehicle Path Following Using Deep Interactive Reinforcement Learning

  • Oct 01, 2022
  • Qilei Zhang +5
  • Dissertation

Towards efficient decision-making : policy compression for reinforcement learning on resource-constrained devices

  • Jan 01, 2025
  • Thomas Avé
  • Research Article
  • Citations164

Intelligent fault diagnosis for rotating machinery using deep Q-network based health state classification: A deep reinforcement learning approach

  • Aug 21, 2019
  • Advanced Engineering Informatics
  • Yu Ding +6
  • Research Article
  • Citations45

PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning

  • May 01, 2020
  • IEEE Journal of Selected Topics in Signal Processing
  • Dor Livne +1
  • Research Article
  • Citations12

Quality Optimization of Adaptive Applications via Deep Reinforcement Learning in Energy Harvesting Edge Devices

  • Nov 01, 2022
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Fupeng Chen +3
  • Research Article
  • Citations33

Intelligent Fault Quantitative Identification for Industrial Internet of Things (IIoT) via a Novel Deep Dual Reinforcement Learning Model Accompanied With Insufficient Samples

  • Oct 15, 2022
  • IEEE Internet of Things Journal
  • Yuanhong Chang +5
  • PDF
  • Research Article
  • Citations11

A Hybrid End-to-End Control Strategy Combining Dueling Deep Q-network and PID for Transient Boost Control of a Diesel Engine with Variable Geometry Turbocharger and Cooled EGR

  • Sep 30, 2019
  • Energies
  • Bo Hu +3
  • Research Article
  • Citations18

Multiobjective Offloading Optimization in Fog Computing Using Deep Reinforcement Learning

  • Jan 01, 2024
  • Journal of Computer Networks and Communications
  • Hojjat Mashal +1
  • Research Article
  • Citations1

Decentralized Computation Offloading Strategy via Multi-Agent Deep Reinforcement Learning for Multi-Access Edge Computing Systems

  • Jan 30, 2026
  • Sensors (Basel, Switzerland)
  • Emmanuella Adu +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.