arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.04750cs.LG
收藏

基于Copula的多Agent模仿学习

Multi-Agent Imitation Learning with Copulas

Stanford University(斯坦福大学)

Hongwei Wang, Lantao Yu, Zhangjie Cao, Stefano Ermon

摘要:

多智能体模仿学习旨在通过学习观察和动作之间的映射来训练多个智能体执行演示任务,这对于理解物理,社会和团队游戏系统至关重要。然而,大多数现有的工作对多智能体交互建模通常假设,代理人作出独立的决定,根据他们的意见,忽略了复杂的依赖代理之间。在本文中,我们建议使用Copula,一个强大的统计工具,捕捉随机变量之间的依赖关系,明确的多智能体系统中的相关性和协调模型。我们提出的模型是能够单独学习的边际捕捉每个个体代理的本地行为模式,以及copula函数,单独和完全捕捉代理之间的依赖结构。在合成和真实世界数据集上进行的大量实验表明,我们的模型在动作预测任务中的各种场景中的表现优于最先进的基线,并且能够生成接近专家演示的新轨迹。

英文摘要:

Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for understanding physical, social, and team-play systems. However, most existing works on modeling multi-agent interactions typically assume that agents make independent decisions based on their observations, ignoring the complex dependence among agents. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents. Extensive experiments on synthetic and real-world datasets show that our model outperforms state-of-the-art baselines across various scenarios in the action prediction task, and is able to generate new trajectories close to expert demonstrations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑