HiSOMA: A hierarchical multi-agent model integrating self-organizing neural networks with multi-agent deep reinforcement learning

• Main Authors: GENG, Minghong, PATERIA, Shubham, SUBAGDJA, Budhitama, TAN, Ah-hwee
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Multi-agent deep reinforcement learning; Hierarchical control; Self-organizing neural networks; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/8927; https://ink.library.smu.edu.sg/context/sis_research/article/9930/viewcontent/HiSOMA_sv.pdf
• Institution: Singapore Management University

Multi-agent deep reinforcement learning (MADRL) has shown remarkable advancements in the past decade. However, most current MADRL models focus on task-specific short-horizon problems involving a small number of agents, limiting their applicability to long-horizon planning in complex environments. Hi...