Multi-Agent Reinforcement Learning Based Coded Computation for Mobile Ad Hoc Computing

TL;DR

This paper introduces a multi-agent reinforcement learning-based coded computation scheme for mobile ad hoc computing, enhancing adaptability, efficiency, and robustness in dynamic, heterogeneous, and unstable network environments.

Contribution

The paper presents a novel MARL-based coded computation scheme tailored for MAHC, addressing challenges of topology changes, link failures, and device heterogeneity with decentralized load allocation.

Findings

Outperforms existing distributed computing schemes in simulations

Demonstrates high adaptability to network topology changes

Shows robustness against system disturbances

Abstract

Mobile ad hoc computing (MAHC), which allows mobile devices to directly share their computing resources, is a promising solution to address the growing demands for computing resources required by mobile devices. However, offloading a computation task from a mobile device to other mobile devices is a challenging task due to frequent topology changes and link failures because of node mobility, unstable and unknown communication environments, and the heterogeneous nature of these devices. To address these challenges, in this paper, we introduce a novel coded computation scheme based on multi-agent reinforcement learning (MARL), which has many promising features such as adaptability to network changes, high efficiency and robustness to uncertain system disturbances, consideration of node heterogeneity, and decentralized load allocation. Comprehensive simulation studies demonstrate that the proposed approach can outperform state-of-the-art distributed computing schemes.