This workshop delves into the dynamic and complex world of multi-agent systems (MAS) operating in challenging environments, where solutions may involve multi-agent reinforcement learning (MARL) or other advanced techniques. Participants are invited to share case studies and real-world applications, showcasing how MAS can drive innovation in areas like embodied agents, autonomous vehicles, robotics, and more.

• 13:30 - 13:40
  Opening
  Speaker: Lei Yuan, Nanjing University

• 13:40-14:05
  Shapley Meets DCOP: A Unified Structural Credit Assignment for Multiagent Planning and Multiagent Reinforcement Learning
  Speaker: Wanyuan Wang, Southeast University

• 14:05-14:30
  Ad Hoc Cooperation: Theoretical Models and Fundamental Limits
  Speaker: Robert Loftin, University of Sheffield

• 14:30-14:55
  From urban network security games to adversarial team games
  Speaker: Youzhi Zhang, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences

• 14:55-15:20
  Cooperative Switching Machines: Reinforcement Learners that assist in their own Learning
  Speaker: David Mguni, Queen Mary University of London

• 15:20-15:35
  Coffee Break

• 15:35-16:00
  Moderate Message Passing Improves Calibration: A Universal Way to Mitigate Confidence Bias in Graph Neural Networks
  Speaker: Xingxing Liang, National University of Defense Technology

• 16:00-16:25
  Multi-agent reinforcement learning for decentralized energy system towards a low-carbon transition
  Speaker: Dawei Qiu, University of Exeter

• 16:25-16:50
  Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach
  Speaker: Weiyu Ma, Chinese Academy of Sciences

• 16:50-17:15
  One by One, Continual Coordinating with Humans via Hyper-Teammate Identification
  Speaker: Feng Chen, Nanjing University

• 17:15 - 17:25
  Closing
  Speaker: Jianhong Wang, University of Bristol