论文标题
基于知识和数据驱动的推理和临时团队的学习
Knowledge-based and Data-driven Reasoning and Learning for Ad Hoc Teamwork
论文作者
论文摘要
我们提出了一个临时团队工作的体系结构，该体系结构指的是在没有事先协调的一组代理团队中的合作。此问题的最新方法通常包括一个数据驱动的组件，该组件使用先前观察的悠久历史来对其他代理（或代理类型）的行为进行建模并确定临时代理的行为。在许多实际领域中，找到大型培训数据集是一项挑战，对于了解和逐步扩展现有模型以说明团队组成或域属性的变化所必需的。我们的架构结合了基于知识和数据驱动的推理和学习原理。具体而言，我们使临时代理能够使用先前的常识域知识和其他代理行为的简单预测模型执行非单调逻辑推理。我们使用基准模拟的多代理协作域Fort Attack来证明我们的体系结构支持适应不可预见的变化，增量学习和对其他代理行为模型的修订，从有限的样本中，在Ad Hoc代理的决策中的透明度，以及比数据驱动基线更好的性能。
We present an architecture for ad hoc teamwork, which refers to collaboration in a team of agents without prior coordination. State of the art methods for this problem often include a data-driven component that uses a long history of prior observations to model the behaviour of other agents (or agent types) and to determine the ad hoc agent's behaviour. In many practical domains, it is challenging to find large training datasets, and necessary to understand and incrementally extend the existing models to account for changes in team composition or domain attributes. Our architecture combines the principles of knowledge-based and data-driven reasoning and learning. Specifically, we enable an ad hoc agent to perform non-monotonic logical reasoning with prior commonsense domain knowledge and incrementally-updated simple predictive models of other agents' behaviour. We use the benchmark simulated multi-agent collaboration domain Fort Attack to demonstrate that our architecture supports adaptation to unforeseen changes, incremental learning and revision of models of other agents' behaviour from limited samples, transparency in the ad hoc agent's decision making, and better performance than a data-driven baseline.
