Publications

Conferences:

• INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning
  The Thirteenth International Conference on Learning Representations (ICLR), in Singapore, 2025
  Yuqian Fu, Yuanheng Zhu, Jian Zhao, Jiajun Chai, and Dongbin Zhao
  

• LDR: Learning Discrete Representation to Improve Noise Robustness in Multi-Agent Tasks
  IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC-S)
  Yuqian Fu, Yuanheng Zhu, Jiajun Chai, and Dongbin Zhao
  

• LILAC: Learning a Leader for Cooperative Reinforcement Learning
  IEEE Conference on Games (CoG), in Beijing, China, 2022
  Yuqian Fu, Jiajun Chai, Yuanheng Zhu, and Dongbin Zhao
  [code]
  

• Diplomancer: Fine-Tuning LLM-Based Autoregressive Factorization Agents for Strategic Decsion-making in Diplomacy
  Forty-Second International Conference on Machine Learning (ICML), in Vancouver, Canada, 2025
  Kaixuan Xu, Jiajun Chai, Sicheng Li, Yuqian Fu, Yuanheng Zhu, and Dongbin Zhao
  

• Meta Learning Task Representation in Multi-Agent Reinforcement Learning: from Global Inference to Local Inference
  IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
  Zijie Zhao, Yuqian Fu, Jiajun Chai, Yuanheng Zhu, and Dongbin Zhao

• Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
  The Thirteenth International Conference on Learning Representations (ICLR), in Singapore, 2025
  Jiajun Chai, Sicheng Li, Yuqian Fu, Dongbin Zhao, Yuanheng Zhu
  

• Offline Goal-Conditioned Reinforcement Learning with Elastic-Subgoal Diffused Policy Learning
  Autonomous Agents and MultiAgent Systems (AAMAS), in Detroit, Michigan, USA, 2025
  Yaocheng Zhang, Yuanheng Zhu, Yuqian Fu, Songjun Tu, Dongbin Zhao
  

• Aligning Credit for Multi-Agent Cooperation via Model-based Counterfactual Imagination
  Autonomous Agents and MultiAgent Systems (AAMAS), in Auckland, New Zealand, 2024
  Jiajun Chai, Yuqian Fu, Dongbin Zhao, and Yuanheng Zhu
  

• E-ACJ: Accurate Junction Extraction For Event Cameras
  IEEE International Conference on Image Processing (ICIP), in Anchorage, Alaska, 2021
  Zhihao Liu and Yuqian Fu
  

Pre-prints

• RLAE: Reinforcement Learning-Assisted Ensemble for LLMs (under review)
  Yuqian Fu, Yuanheng Zhu, Jiajun Chai, Guojun Yin, Wei Lin, Qichao Zhang and Dongbin Zhao
  

• CPEG: Leveraging Consistency Policy with Consensus Guidance for Multi-agent Exploration (under review)
  Yuqian Fu, Zijie Zhao, Yuanheng Zhu, Haoran Li, Jiajun Chai, and Dongbin Zhao
  

• AVA: Attentive VLM Agent for Mastering StarCraft II (under review)
  Weiyu Ma\(^*\), Yuqian Fu\(^*\), Zecheng Zhang, and Guohao Li
  

• Learning and Planning Multi-Agent Tasks via a MoE-based World Model (under review)
  Zijie Zhao, Zhao Zhongyue, Yuqian Fu, Yuanheng Zhu, and Dongbin Zhao