Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination
The breakthrough and progress of intelligent gaming technology with deep reinforcement learning as the core in the field of games provide a method reference for the research of agents in sea-air wargames. The architecture design of the agent is the primary core key problem that needs to be solved, a...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Command Control and Simulation
2024-04-01
|
| Series: | Zhihui kongzhi yu fangzhen |
| Subjects: | |
| Online Access: | https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1711964807320-1620836864.pdf |
| _version_ | 1827298362274086912 |
|---|---|
| author | SU Jiongming, LUO Junren, CHEN Shaofei, XIANG Fengtao |
| author_facet | SU Jiongming, LUO Junren, CHEN Shaofei, XIANG Fengtao |
| author_sort | SU Jiongming, LUO Junren, CHEN Shaofei, XIANG Fengtao |
| collection | DOAJ |
| description | The breakthrough and progress of intelligent gaming technology with deep reinforcement learning as the core in the field of games provide a method reference for the research of agents in sea-air wargames. The architecture design of the agent is the primary core key problem that needs to be solved, and a good architecture can reduce the complexity and difficulty of training and accelerate the convergence of policies. A stochastic game model of sea-air cross-domain cooperative decision-making has been proposed, and its corresponding equilibrium solution concepts have been analyzed. Based on the analysis of typical agent frameworks, aiming at the decision-making gaming process of sea-air wargames, and then an agent bi-level architecture based on multi-Agent hierarchical reinforcement learning is proposed, which can effectively solve the problems of collaboration and dimensional disaster. The key technologies are analyzed from four aspects: force coordination, agent network design, adversary modeling and training mechanism. Hoping to provide architectural guidance for the subsequent design and implementation of sea-air wargaming agents. |
| first_indexed | 2024-04-24T15:13:39Z |
| format | Article |
| id | doaj.art-37eb8ca36bf14564857c59bf06f0c95d |
| institution | Directory Open Access Journal |
| issn | 1673-3819 |
| language | zho |
| last_indexed | 2024-04-24T15:13:39Z |
| publishDate | 2024-04-01 |
| publisher | Editorial Office of Command Control and Simulation |
| record_format | Article |
| series | Zhihui kongzhi yu fangzhen |
| spelling | doaj.art-37eb8ca36bf14564857c59bf06f0c95d2024-04-02T09:51:41ZzhoEditorial Office of Command Control and SimulationZhihui kongzhi yu fangzhen1673-38192024-04-01462354310.3969/j.issn.1673-3819.2024.02.006Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordinationSU Jiongming, LUO Junren, CHEN Shaofei, XIANG Fengtao0College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaThe breakthrough and progress of intelligent gaming technology with deep reinforcement learning as the core in the field of games provide a method reference for the research of agents in sea-air wargames. The architecture design of the agent is the primary core key problem that needs to be solved, and a good architecture can reduce the complexity and difficulty of training and accelerate the convergence of policies. A stochastic game model of sea-air cross-domain cooperative decision-making has been proposed, and its corresponding equilibrium solution concepts have been analyzed. Based on the analysis of typical agent frameworks, aiming at the decision-making gaming process of sea-air wargames, and then an agent bi-level architecture based on multi-Agent hierarchical reinforcement learning is proposed, which can effectively solve the problems of collaboration and dimensional disaster. The key technologies are analyzed from four aspects: force coordination, agent network design, adversary modeling and training mechanism. Hoping to provide architectural guidance for the subsequent design and implementation of sea-air wargaming agents.https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1711964807320-1620836864.pdfsea-air wargame|cross-domain cooperation|wargaming|multi-agent|intelligent gaming|model architecture|hierarchical reinforcement learning |
| spellingShingle | SU Jiongming, LUO Junren, CHEN Shaofei, XIANG Fengtao Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination Zhihui kongzhi yu fangzhen sea-air wargame|cross-domain cooperation|wargaming|multi-agent|intelligent gaming|model architecture|hierarchical reinforcement learning |
| title | Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination |
| title_full | Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination |
| title_fullStr | Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination |
| title_full_unstemmed | Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination |
| title_short | Architecture design and key technologies analysis of wargaming AI for sea-air cross-domain coordination |
| title_sort | architecture design and key technologies analysis of wargaming ai for sea air cross domain coordination |
| topic | sea-air wargame|cross-domain cooperation|wargaming|multi-agent|intelligent gaming|model architecture|hierarchical reinforcement learning |
| url | https://www.zhkzyfz.cn/fileup/1673-3819/PDF/1711964807320-1620836864.pdf |
| work_keys_str_mv | AT sujiongmingluojunrenchenshaofeixiangfengtao architecturedesignandkeytechnologiesanalysisofwargamingaiforseaaircrossdomaincoordination |