会议ICRA发表论文:基于排列不变评价器的人工辅助重组多智能体强化学习

论文“Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning”被机器人顶会ICRA接收

时间:2025-01-28

关键词:脑机接口与智能机器人,文章接收

  近日,硕士研究生胡华文在全球机器人和自动化领域的顶级学术会议(IEEE International Conference on Robotics & Automation)发表题为“Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning”的研究性文章,通讯作者为张枢教授。

  Human-in-the-loop reinforcement learning integrates human expertise to accelerate agent learning and provide critical guidance and feedback in complex fields. However, many existing approaches focus on single-agent tasks and require continuous human involvement during the training process, significantly increasing the human workload and limiting scalability. In this paper, we propose HARP (Human-Assisted Regrouping with Permutation Invariant Critic,图1), a multi-agent reinforcement learning framework designed for group-oriented tasks. HARP integrates automatic agent regrouping with strategic human assistance during deployment, enabling and allowing non-experts to offer effective guidance with minimal intervention. During training, agents dynamically adjust their groupings to optimize collaborative task completion. When deployed, they actively seek human assistance and utilize the Permutation Invariant Group Critic(图2) to evaluate and refine human-proposed groupings, allowing non-expert users to contribute valuable suggestions. In multiple collaboration scenarios, our approach is able to leverage limited guidance from non-experts and enhance performance.

图1:HARP模型框架 图1:HARP模型框架
图2:排列不变分组评价器 图2:排列不变分组评价器

参考文献

Huawen Hu, Enze Shi, Chenxi Yue, Shuocun Yang, Zihao Wu, Yiwei Li, Tianyang Zhong, Tuo Zhang, Tianming Liu, Shu Zhang. HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning [C]//2025 IEEE International Conference on Robotics and Automation (ICRA). 2025.

https://www.sciencedirect.com/science/article/pii/S0010482524017141