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 2406.14746cs.LGcs.RO
收藏

受行为启发的神经网络用于关系推断

Behavior-Inspired Neural Networks for Relational Inference

Princeton University(普林斯顿大学)

Yulong Yang, Bowen Feng, Keqin Wang, Naomi Ehrich Leonard, Adji Bousso Dieng, Christine Allen-Blanchette

AI总结:

本文提出在可观测行为与潜在关系类别之间引入抽象层级,将学习到的类别偏好与智能体邻近性整合进非线性观点动力学模型,以自然识别互斥关系类别、预测智能体演化并控制行为,并通过实验验证其在可解释类别学习和长时域轨迹预测中的有效性。

摘要:

从行人到Kuramoto振子,智能体之间的交互支配着动力系统在空间和时间中的演化方式。发现这些智能体如何相互关联,有可能提升我们对这些系统背后通常十分复杂的动力学的理解。近期工作基于对智能体物理行为的观测来学习对智能体之间关系的分类。这些方法将关系类别建模为分类分布的结果,这种做法具有局限性,并且与现实世界系统相悖,因为在现实系统中,关系类别常常相互交织并发生交互。在本工作中,我们在智能体的可观测行为与决定其行为的潜在类别之间引入了一个抽象层级。为此,我们学习一个从智能体观测到智能体对一组潜在类别偏好的映射。学习到的偏好和智能体间邻近性被整合到一个非线性观点动力学模型中,这使我们能够自然地识别互斥类别、预测智能体随时间的演化,并控制智能体的行为。通过大量实验,我们证明了该模型在学习可解释类别方面的实用性,以及该模型在长时域轨迹预测中的有效性。

英文摘要:

From pedestrians to Kuramoto oscillators, interactions between agents govern how dynamical systems evolve in space and time. Discovering how these agents relate to each other has the potential to improve our understanding of the often complex dynamics that underlie these systems. Recent works learn to categorize relationships between agents based on observations of their physical behavior. These approaches model relationship categories as outcomes of a categorical distribution which is limiting and contrary to real-world systems, where relationship categories often intermingle and interact. In this work, we introduce a level of abstraction between the observable behavior of agents and the latent categories that determine their behavior. To do this, we learn a mapping from agent observations to agent preferences for a set of latent categories. The learned preferences and inter-agent proximity are integrated in a nonlinear opinion dynamics model, which allows us to naturally identify mutually exclusive categories, predict an agent's evolution in time, and control an agent's behavior. Through extensive experiments, we demonstrate the utility of our model for learning interpretable categories, and the efficacy of our model for long-horizon trajectory prediction.

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。

↑