CA-MARL: credit-aware multi-agent reinforcement learning for USV pursuit–evasion missions under complex maritime disturbances

Tian, Shunyu, Tao, Weiyu, Wu, Xiangyu, Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 and Wei, Changyun 2026. CA-MARL: credit-aware multi-agent reinforcement learning for USV pursuit–evasion missions under complex maritime disturbances. Maritime Engineering 10.1680/jmaen.26.00013

Full text not available from this repository.

Abstract

Multi-unmanned surface vehicle (USV) pursuit–evasion missions in maritime environments presents significant challenges due to dynamic ship populations, high-dimensional observations, and the gap between idealised simulations and real-world maritime physics. To address these challenges, we propose a Credit-Aware Multi-Agent Reinforcement Learning (CA-MARL) framework for multi-USV pursuit–evasion. The framework features two key innovations: a Residual Self-Attention module that adapts to varying fleet sizes through permutation-invariant attention, and a Mixed Credit Assignment module that enhances centralised value estimation with decentralised branches. Moreover, to bridge the simulation-to-reality gap, we develop a high-fidelity 3D virtual platform using Unity3D that incorporates maritime factors, such as hydrodynamics and wave disturbances, which are typically overlooked in USV simulations but critical for maritime operations. Experiments demonstrate that our method achieves superior coordination, sample efficiency, and policy robustness compared to existing baselines, providing a credible foundation for deploying MARL policies in realistic multi-USV scenarios.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Schools > Engineering
Publisher:	ICE Publishing
ISSN:	1741-7597
Date of Acceptance:	29 April 2026
Last Modified:	14 Aug 2026 10:00
URI:	https://orca.cardiff.ac.uk/id/eprint/188991

Actions (repository staff only)

Edit Item