Meta-reinforcement learning driven model architecture and algorithm optimization in intelligent driving task offloading

doi:10.1016/j.comcom.2025.108310

Meta-reinforcement learning driven model architecture and algorithm optimization in intelligent driving task offloading

2025-08-19

0

PRE

AI

Konstantin Igorevich Kostromitin

DOI：10.1016/j.comcom.2025.108310

Original

Original request for help

Save

Abstract

En 中文

In the process of rapid development of intelligent driving technology, the amount of data generated by vehicles increases dramatically, while the bottleneck of storage and computation capacity of in-vehicle devices becomes more and more prominent, and task offloading becomes the key to improve the performance of intelligent driving systems. In this context, this paper proposes the MRL-ADTO algorithm, which innovatively applies meta-reinforcement learning (MRL) to the field of intelligent driving task offloading, optimizes the directed acyclic graph (DAG) synthesis logic and the task priority ranking algorithm, designs a neural network model based on the sequence to sequence (Seq2Seq) structure, and introduces the mechanism of multi-head attention at the same time. The experimental results show that MRL-ADTO can significantly reduce the task execution delay in multiple scenarios compared with the existing algorithms, and has obvious advantages in terms of training efficiency and convergence performance, providing an efficient and reliable solution for smart driving task offloading.

Keywords:

meta-reinforcement learning

task offloading

intelligent driving

directed acyclic graph

sequence to sequence

Meta-reinforcement learning driven model architecture and algorithm optimization in intelligent driving task offloading

Abstract

Journal

Organization