强化学习，多智能体系统(RL agent and LLM agent)

招收硕士研究生，也非常欢迎以RA的形式加入课题组，通过共同合作互相了解。欢迎感兴趣的同学通过邮件联系我！

   

（1） DR2: Revisiting Visual Reinforcement Learning from the Dimensional Analysis Perspective, AAMAS2026, 2026, 第 1 作者
（2） TMAE: Learning Targeted Multi-Agent Exploration via Causal Inference, AAAI2026, 2026, 第 1 作者
（3） M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference, AAAI2026, 2026, 第 1 作者
（4） Group Causal Policy Optimization for Post-Training Large Language Models, AAAI2026, 2026, 第 4 作者
（5） Loss of Plasticity: A New Perspective on Solving Multi-Agent Exploration for Sparse Reward Tasks, AAMAS2025, 2025, 第 2 作者  通讯作者
（6） Supporting vision-language model few-shot inference with confounder-pruned knowledge prompt, NEURAL NETWORKS, 2025, 第 4 作者  通讯作者
（7） Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective, INTERNATIONAL JOURNAL OF COMPUTER VISION, 2025, 第 4 作者
（8） Revisiting Communication Efficiency in Multi-Agent Reinforcement Learning from the Dimensional Analysis Perspective, AAMAS2025, 2025, 第 1 作者
（9） Visual Reinforcement Learning via Sequential Consistency Preserved Policy Contrast from Optimal Transport View, Neural Networks, 2025, 第 3 作者  通讯作者
（10） T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration, AAAI2024, 2024, 第 1 作者