Cooperative Multiagent Learning and Exploration With Min-Max Intrinsic Motivation

• Published in: IEEE transactions on cybernetics Vol. 55; no. 6; pp. 2852 - 2864
• Main Authors: Hou, Yaqing, Kang, Jie, Piao, Haiyin, Zeng, Yifeng, Ong, Yew-Soon, Jin, Yaochu, Zhang, Qiang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2025
• Subjects: Artificial intelligence; Cooperation; Entropy; Estimation; exploration; Minimization; multiagent reinforcement learning (MARL); multiagent systems; Mutual information; Optimization; Reinforcement learning; Space exploration; Training; Uncertainty

In the field of multiagent reinforcement learning (MARL), the ability to effectively explore unknown environments and collect information and experiences that are most beneficial for policy learning represents a critical research area. However, existing work often encounters difficulties in addressi...