AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

被引:4
|
作者
Rahman, Aowabin [1 ]
Bhattacharya, Arnab [1 ]
Ramachandran, Thiagarajan [1 ]
Mukherjee, Sayak [1 ]
Sharma, Himanshu [1 ]
Fujimoto, Ted [2 ]
Chatterjee, Samrat [3 ]
机构
[1] Pacific Northwest Natl Lab, Optimizat & Control Grp, Richland, WA USA
[2] Pacific Northwest Natl Lab, Data Analyt Grp, Richland, WA USA
[3] Pacific Northwest Natl Lab, Data Sci & Machine Intelligence Grp, Richland, WA USA
关键词
Search and Rescue; Multi-agent Reinforcement Learning; Adversarial Reinforcement Learning; Critical Infrastructure Security;
D O I
10.1109/HST56032.2022.10025434
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-oriented coordination and collaboration. Often, SAR coordination strategies are manually designed by human experts who can remotely control the multi-robot system and enable semi-autonomous operations. However, in remote environments where connectivity is limited and human intervention is often not possible, decentralized collaboration strategies are needed for fully-autonomous operations. Nevertheless, decentralized coordination may be ineffective in adversarial environments due to sensor noise, actuation faults, or manipulation of inter-agent communication data. In this paper, we propose an algorithmic approach based on adversarial multi-agent reinforcement learning (MARL) that allows robots to efficiently coordinate their strategies in the presence of adversarial inter-agent communications. In our setup, the objective of the multi-robot team is to discover targets strategically in an obstacle-strewn geographical area by minimizing the average time needed to find the targets. It is assumed that the robots have no prior knowledge of the target locations, and they can interact with only a subset of neighboring robots at any time. Based on the centralized training with decentralized execution (CTDE) paradigm in MARL, we utilize a hierarchical meta-learning framework to learn dynamic team-coordination modalities and discover emergent team behavior under complex cooperative-competitive scenarios. The effectiveness of our approach is demonstrated on a collection of prototype grid-world environments with different specifications of benign and adversarial agents, target locations, and agent rewards.
引用
收藏
页数:7
相关论文
共 50 条
  • [41] Learning to Share in Multi-Agent Reinforcement Learning
    Yi, Yuxuan
    Li, Ge
    Wang, Yaowei
    Lu, Zongqing
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [42] Multi-Agent Reinforcement Learning for Microgrids
    Dimeas, A. L.
    Hatziargyriou, N. D.
    IEEE POWER AND ENERGY SOCIETY GENERAL MEETING 2010, 2010,
  • [43] Multi-agent Exploration with Reinforcement Learning
    Sygkounas, Alkis
    Tsipianitis, Dimitris
    Nikolakopoulos, George
    Bechlioulis, Charalampos P.
    2022 30TH MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED), 2022, : 630 - 635
  • [44] Hierarchical multi-agent reinforcement learning
    Ghavamzadeh, Mohammad
    Mahadevan, Sridhar
    Makar, Rajbala
    AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2006, 13 (02) : 197 - 229
  • [45] Partitioning in multi-agent reinforcement learning
    Sun, R
    Peterson, T
    FROM ANIMALS TO ANIMATS 6, 2000, : 325 - 332
  • [46] The Dynamics of Multi-Agent Reinforcement Learning
    Dickens, Luke
    Broda, Krysia
    Russo, Alessandra
    ECAI 2010 - 19TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2010, 215 : 367 - 372
  • [47] Multi-agent reinforcement learning: A survey
    Busoniu, Lucian
    Babuska, Robert
    De Schutter, Bart
    2006 9TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION, VOLS 1- 5, 2006, : 1133 - +
  • [48] MARRGM: Learning Framework for Multi-Agent Reinforcement Learning via Reinforcement Recommendation and Group Modification
    Wu, Peiliang
    Tian, Liqiang
    Zhang, Qian
    Mao, Bingyi
    Chen, Wenbai
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (06) : 5385 - 5392
  • [49] Multi-UAV Escape Target Search: A Multi-Agent Reinforcement Learning Method
    Liao, Guang
    Wang, Jian
    Yang, Dujia
    Yang, Junan
    SENSORS, 2024, 24 (21)
  • [50] ADVERSARIAL MULTI-AGENT REINFORCEMENT LEARNING ALGORITHM FOR ANOMALY NETWORK INTRUSION DETECTION SYSTEM
    Mohamed, Safa
    Ejbali, Ridha
    INTERNATIONAL JOURNAL ON INFORMATION TECHNOLOGIES AND SECURITY, 2021, 13 (03): : 87 - 102