This paper aims to enable multi-agent systems to effectively utilize past memories to adapt to novel collaborative tasks in a data-efficient fashion. We propose the Multi-Agent Coordination Skill Database, a repository for storing a collection of coordinated behaviors associated with key vectors distinctive to them. Our Transformer-based skill encoder effectively captures spatio-temporal interactions that contribute to coordination and provides a unique skill representation for each coordinated behavior. By leveraging a small number of demonstrations of the target task, the database enables us to train the policy using a dataset augmented with the retrieved demonstrations. Experimental evaluations demonstrate that our method achieves a significantly higher success rate in push manipulation tasks compared with baseline methods like few-shot imitation learning. Furthermore, we validate the effectiveness of our retrieve-and-learn framework in a real environment using a team of wheeled robots.

翻译：本文旨在使多智能体系统能够以数据高效的方式有效利用过往记忆，适应新型协作任务。我们提出多智能体协调技能数据库，该数据库存储一系列协调行为及其对应的关键特征向量。基于Transformer的技能编码器能有效捕获促成协调的时空交互模式，并为每个协调行为提供独特的技能表征。通过利用目标任务的小样本演示，该数据库使我们能够用检索到的演示增强训练数据集来训练策略。实验评估表明，在推操作任务中，我们的方法相较于少样本模仿学习等基线方法实现了显著更高的成功率。此外，我们利用一组轮式机器人在真实环境中验证了该"检索-学习"框架的有效性。