arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.11044cs.LGcs.AIcs.MAstat.ML
收藏

多Agent学习的关系前向模型

Relational Forward Models for Multi-Agent Learning

DeepMind(深度思维);Imperial College London(帝国理工学院)

Andrea Tacchetti, H. Francis Song, Pedro A. M. Mediano, Vinicius Zambaldi, Neil C. Rabinowitz, Thore Graepel, Matthew Botvinick, Peter W. Battaglia

摘要:

多智能体系统的行为动力学具有丰富而有序的结构,可以利用这些结构来理解这些系统,并改进人工智能体如何学习在其中操作。在这里,我们介绍了用于多智能体学习的关系前向模型(RFM),该网络可以学习对多智能体环境中智能体的未来行为进行准确预测。由于这些模型对环境中存在的离散实体和关系进行操作,因此它们产生了可解释的中间表示,这些中间表示提供了对驱动代理行为的原因以及哪些事件介导了社会互动的强度和效价的见解。此外,我们表明,嵌入RFM模块内代理的结果更快的学习系统相比,非增强基线。随着越来越多的自治系统,我们开发和互动,成为多智能体的性质,开发更丰富的分析工具,以表征如何以及为什么代理决策是越来越必要的。此外,开发快速安全地学会相互协调以及与共享环境中的人类协调的人工智能至关重要。

英文摘要:

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to make accurate predictions of agents' future behavior in multi-agent environments. Because these models operate on the discrete entities and relations present in the environment, they produce interpretable intermediate representations which offer insights into what drives agents' behavior, and what events mediate the intensity and valence of social interactions. Furthermore, we show that embedding RFM modules inside agents results in faster learning systems compared to non-augmented baselines. As more and more of the autonomous systems we develop and interact with become multi-agent in nature, developing richer analysis tools for characterizing how and why agents make decisions is increasingly necessary. Moreover, developing artificial agents that quickly and safely learn to coordinate with one another, and with humans in shared environments, is crucial.

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。

↑