MetaTOC stay on top of your field, easily

Mobile robot path planning based on the improved DDPG algorithm

, , , , ,

Transactions of the Institute of Measurement and Control

Published online on

Abstract

Transactions of the Institute of Measurement and Control, Ahead of Print.
An improved Deep Deterministic Policy Gradient (DDPG) algorithm, integrating self-attention mechanisms, adversarial training, and prioritized experience replay, is proposed to address the limitations of state representation capability, sample efficiency, ...