arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.03291cs.LGcs.MA
收藏

baller2vec:一个多主体时空建模的多实体Transformer

baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling

Auburn University(奥本大学)

Michael A. Alcorn, Anh Nguyen

摘要:

从算法设计和计算复杂性的角度来看,多智能体时空建模都是一项具有挑战性的任务。最近的工作已经探索了传统的深度顺序模型在这一领域的有效性,但这些架构是缓慢和繁琐的训练,特别是随着模型大小的增加。此外,之前对代理之间跨时间交互进行建模的尝试也有局限性,例如对代理施加命令,或对它们的关系做出假设。在本文中,我们介绍了baller2vec,一个多实体的标准Transformer的推广,可以在最小的假设,同时,有效地整合跨实体和时间的信息。我们通过训练baller2vec执行两个不同的篮球相关任务来测试其用于多智能体时空建模的有效性:(1)同时对球场上所有球员的轨迹进行建模,以及(2)对球的轨迹进行建模。baller2vec不仅能够很好地完成这些任务(远远优于具有类似参数数量的图递归神经网络),而且似乎还能够“理解”篮球比赛,在其嵌入中编码球员的特质,并使用其注意力头执行篮球相关功能。

英文摘要:

Multi-agent spatiotemporal modeling is a challenging task from both an algorithmic design and computational complexity perspective. Recent work has explored the efficacy of traditional deep sequential models in this domain, but these architectures are slow and cumbersome to train, particularly as model size increases. Further, prior attempts to model interactions between agents across time have limitations, such as imposing an order on the agents, or making assumptions about their relationships. In this paper, we introduce baller2vec, a multi-entity generalization of the standard Transformer that can, with minimal assumptions, simultaneously and efficiently integrate information across entities and time. We test the effectiveness of baller2vec for multi-agent spatiotemporal modeling by training it to perform two different basketball-related tasks: (1) simultaneously modeling the trajectories of all players on the court and (2) modeling the trajectory of the ball. Not only does baller2vec learn to perform these tasks well (outperforming a graph recurrent neural network with a similar number of parameters by a wide margin), it also appears to "understand" the game of basketball, encoding idiosyncratic qualities of players in its embeddings, and performing basketball-relevant functions with its attention heads.

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。

↑