Broad agents

Broad agents
复制标题

广泛代理

DOI:
10.1145/122344.122350
复制
发表时间:
1991
期刊:
SIGART Bull.
影响因子:
--
通讯作者:
W. S. Reilly
W. S. Reilly
中科院分区:
--
文献类型:
--
作者:
J. Bates;Bryan Loyall;W. S. Reilly

文献摘要

被引文献

相似文献

卡内基梅隆大学的奥兹项目正在为戏剧性的虚拟世界开发技术。这样的世界的一个必要条件是存在广泛的(尽管可能是肤浅的)代理人。为了支持我们的需求,我们正在开发一个代理架构,它提供目标和目标导向的反应行为、情绪状态及其对行为的影响、一些自然语言能力(特别是基于语用学的语言生成),以及一些记忆和推理能力。只要有必要,我们就会限制这些能力中的每一种,以使我们能够建立一个具有广泛能力的综合代理机构。在试图构建一个广泛的代理时,体系结构的组件之间似乎出现了约束。在本文中,我们将讨论其中的一些约束。
The Oz project at Carnegie Mellon is developing technology for dramatic virtual worlds. One requirement of such worlds is the presence of broad, though perhaps shallow, agents. To support our needs, we are developing an agent architecture that provides goals and goal directed reactive behavior, emotional state and its effects on behavior, some natural language abilities (especially pragmatics based language generation), and some memory and inference abilities. We are limiting each of these capacities whenever necessary to allow us to build a broadly capable, integrated agent.In attempting to construct a broad agent, constraints seem to arise between components of the architecture. In this brief note, we discuss some of these constraints.