Hierarchical control of multi-agent reinforcement learning team in real-time strategy (RTS) games

• Main Authors: ZHOU, Weigui Jair, SUBAGDJA, Budhitama, TAN, Ah-hwee, ONG, Darren Wee Sze
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Hierarchical control; Self-organizing neural networks; Reinforcement learning; Real-time strategy games; Artificial Intelligence and Robotics; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/6242; https://ink.library.smu.edu.sg/context/sis_research/article/7245/viewcontent/manuscript_ESWA_S_21_0154_R1_27062021.pdf
• Institution: Singapore Management University

Coordinated control of multi-agent teams is an important task in many real-time strategy (RTS) games. In most prior work, micromanagement is the commonly used strategy whereby individual agents operate independently and make their own combat decisions. On the other extreme, some employ a macromanage...