让AI在无预设协作中快速推理，结合常识与动态学习。
Generic-to-Specific Reasoning and Learning for Scalable Ad Hoc Teamwork
- 用非单调逻辑融合常识、行为预测和通用目标推演
- 在虚拟环境测试中实现多智能体高效自适应协作
- 适合需快速响应变化的实时协作场景
部署在辅助角色中的AI智能体常需在无事先协调的情况下与其他智能体（人类或AI系统）协作。当前最先进的方法多采用依赖大量标注数据的数据驱动策略，缺乏透明性且难以快速更新知识以应对变化。随着智能体数量增加，决策复杂度上升，协作效率下降。本文提出结合知识驱动与数据驱动方法的优势，构建用于即兴协作的推理与学习架构。针对任意目标，每个即兴智能体可通过非单调逻辑推理，结合：(a) 先验的常识性领域知识；(b) 快速学习并更新的其他智能体行为预测模型；(c) 基于现有基础模型中相似情境的通用知识所预期的抽象未来目标，自主决定行动。我们在一个真实的物理驱动3D仿真环境VirtualHome中对本架构进行了实验评估。
原文摘要 · Abstract (English)
AI agents deployed in assistive roles often have to collaborate with other agents (humans, AI systems) without prior coordination. Methods considered state of the art for such ad hoc teamwork often pursue a data-driven approach that needs a large labeled dataset of prior observations, lacks transparency, and makes it difficult to rapidly revise existing knowledge in response to changes. As the number of agents increases, the complexity of decision-making makes it difficult to collaborate effectively. This paper advocates leveraging the complementary strengths of knowledge-based and data-driven methods for reasoning and learning for ad hoc teamwork. For any given goal, our architecture enables each ad hoc agent to determine its actions through non-monotonic logical reasoning with: (a) prior commonsense domain-specific knowledge; (b) models learned and revised rapidly to predict the behavior of other agents; and (c) anticipated abstract future goals based on generic knowledge of similar situations in an existing foundation model. We experimentally evaluate our architecture's capabilities in VirtualHome, a realistic physics-based 3D simulation environment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。