An advanced-PER based deep reinforcement learning method for adversarial maritime mission planning

Author Identifier (ORCID)

Jianxin Li’s ORCID record ORCID Logo

Abstract

Maritime confrontation mission planning is a difficult task planning problem. The difficulty of planning stems from the dynamic characteristics and high complexity of the maritime environment. These factors make it extremely difficult to describe the state and refine the decision level. Traditional task planning methods based on rules or optimization algorithms suffer from limitations in dealing with these problems. They are not adaptable to dynamic environments, and the decision level is too rough. This paper proposes an Advanced-PER based Deep Reinforcement Learning Method based on double deep Q-Network (DDQN) for complex maritime confrontation task planning problems, and a new Prioritized Experience Replay method is introduced to improve the deep reinforcement learning method. The model significantly improves the learning efficiency and decision-making performance of the model by partitioning the storage experience and dynamically balancing the adoption ratio of different action experiences. Experimental results indicate the effectiveness of the proposed method.

Keywords

adversarial maritime mission planning, deep reinforcement learning, experience replay

Document Type

Conference Proceeding

Date of Publication

1-1-2026

ISSN

03029743

Volume

16367 LNCS

Publication Title

Lecture Notes in Computer Science

Publisher

Springer

School

School of Business and Law

ISBN

[9789819573936]

Copyright

subscription content

Content Type

Metadata only

First Page

337

Last Page

347

Recommended Citation

Li, M., Wang, C., Wang, Y., Zhang, X., Huang, X., Li, B., Li, J., & Chen, Y. (2026). An advanced-PER based deep reinforcement learning method for adversarial maritime mission planning. In International Conference on Web Information Systems Engineering (pp. 337-347). Springer Nature. https://doi.org/10.1007/978-981-95-7394-3_23

Share

 
COinS
 

Link to publisher version (DOI)

10.1007/978-981-95-7394-3_23