Streamlined AI architecture for wargaming

被引:0
|
作者
Rose, Melanie A. [1 ]
Ryer, Shaun M. [1 ]
机构
[1] Air Force Res Lab, Informat Directorate, 525 Brooks Rd, Rome, NY 13441 USA
关键词
Reinforcement Learning; Wargaming;
D O I
10.1117/12.3012668
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Legatus AI, an Air Force program supporting joint and coalition partners, is addressing the need for the creation of a common architecture of software and hardware for campaign level planning to empower the efficient development of AI and core AI capabilities. Building off lessons learned in previous command and control programs, Legatus AI seeks to close the capability gap by transforming AI development from non-reusable boutique solutions to an ecosystem of modular and reusable processes for configuring, training, evaluating, and deploying reinforcement learning and game theory agents for planning and wargaming environments. The prototype architecture added reinforcement learning capabilities to StreamlinedML to allow for communication between AI agents and games using a Docker-based solution. The architecture was tested on the Airlift Challenge simulation to ensure intended functionality and demonstrate the initial capability. Future work will incorporate additional agents and Unity-based wargames. The maturation of this architecture is a key cornerstone for future collaborative research and development of adaptable AI and plug-and-play wargaming platforms.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Generative AI and Wargaming: What is it Good For?
    Hinton, Patrick
    RUSI JOURNAL, 2023, 168 (07): : 34 - 41
  • [2] AI-enabled wargaming in the Military Decision Making Process
    Schwartz, Peter J.
    O'Neill, Daniel, V
    Bentz, Meghan E.
    Brown, Adam
    Doyle, Brian S.
    Liepa, Olivia C.
    Lawrence, Robert
    Hull, Richard D.
    ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS II, 2020, 11413
  • [3] Applying Deep Reinforcement Learning to Train AI Agents in a Wargaming Framework
    Rinaudo, Christina H.
    Leonard, William B.
    Hopson, Jaylen E.
    Coumbe, Theresa R.
    Pettitt, James A.
    Darken, Christian
    SOUTHEASTCON 2024, 2024, : 1131 - 1136
  • [4] STREAMLINED ARCHITECTURE ACHIEVES SOFTWARE COMPATIBILITY
    SCHWERMER, HR
    ELECTRONICS, 1979, 52 (23): : 119 - 120
  • [5] Wargaming as a Methodology: The International Crisis Wargame and Experimental Wargaming
    Schechter, Benjamin
    Schneider, Jacquelyn
    Shaffer, Rachael
    SIMULATION & GAMING, 2021, 52 (04) : 513 - 526
  • [6] A STREAMLINED ENCODER/DECODER ARCHITECTURE FOR MELODY EXTRACTION
    Hsieh, Tsung-Han
    Su, Li
    Yang, Yi-Hsuan
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 156 - 160
  • [7] AI art in architecture
    Joern Ploennigs
    Markus Berger
    AI in Civil Engineering, 2 (1):
  • [8] The road ahead for wargaming: The why and how of achieving the next generation of wargaming
    Caffrey, MB
    ENABLING TECHNOLOGIES FOR SIMULATION SCIENCE VIII, 2004, 5423 : 160 - 168
  • [9] The Application of AlphaZero to Wargaming
    Moy, Glennn
    Shekh, Slava
    AI 2019: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, 11919 : 3 - 14
  • [10] Wargaming: a structured conversation
    Appleget, Jeffrey
    JOURNAL OF DEFENSE MODELING AND SIMULATION-APPLICATIONS METHODOLOGY TECHNOLOGY-JDMS, 2022,