arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09586cs.AI
收藏

利用干预学习自主智能体的因果模型

Learning Causal Models of Autonomous Agents using Interventions

Arizona State University(亚利桑那州立大学)

Pulkit Verma, Siddharth Srivastava

摘要:

人工智能系统广泛使用的几个障碍之一是缺乏可解释性的要求,这种要求可以使外行人确保此类系统的安全和可靠的行为。我们扩展了代理评估模块的分析,该模块让AI系统在模拟器中执行高级指令序列,并回答用户对其执行动作序列的查询。我们表明,这样一个原始的查询响应能力是足够的,有效地获得一个用户可解释的因果模型的系统在固定的,完全可观察的,和确定性的设置。我们还介绍了动态因果决策网络(DCDN),捕捉因果结构的STRIP样域。不同类别的查询的比较分析,也提出了在回答他们所需的计算要求和所需的努力,以评估他们的反应,学习正确的模型。

英文摘要:

One of the several obstacles in the widespread use of AI systems is the lack of requirements of interpretability that can enable a layperson to ensure the safe and reliable behavior of such systems. We extend the analysis of an agent assessment module that lets an AI system execute high-level instruction sequences in simulators and answer the user queries about its execution of sequences of actions. We show that such a primitive query-response capability is sufficient to efficiently derive a user-interpretable causal model of the system in stationary, fully observable, and deterministic settings. We also introduce dynamic causal decision networks (DCDNs) that capture the causal structure of STRIPS-like domains. A comparative analysis of different classes of queries is also presented in terms of the computational requirements needed to answer them and the efforts required to evaluate their responses to learn the correct model.

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。

↑