Interpreting actions by attributing compositional desires
Interpreting actions by attributing compositional desires
复制标题
通过归因组合欲望来解释动作
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
J. Jara
中科院分区：
文献类型：
--
作者：
Joey Velez;Max H. Siegel;J. Tenenbaum;J. Jara
我们看不到别人的心理状态，所以我们通过观察别人的行为来推断他们的心理状态。理性行为模型中的贝叶斯推理（称为逆向规划）捕捉了人类如何从可观察的行为中推断出欲望。这些模型将愿望表示为主体与世界国家之间的简单关联。在本文中，我们表明，通过将欲望表示为概率程序，逆向规划模型可以推断出复杂行为背后的复杂欲望——具有时间和逻辑结构的欲望，可以通过不同的方式实现。我们的模型通过逻辑原语结合了基本愿望，受到最近基于概率语法的概念学习模型的启发。通过参数改变行为的实验，我们表明我们的模型可以高精度预测人们如何推断复杂的欲望。我们的工作揭示了心理状态背后的表征，并为能够像我们一样推理他人思想的算法铺平了道路。
We cannot see others’ mental states, so we infer them by watching how people behave. Bayesian inference in a model of rational action – called inverse planning – captures how humans infer desires from observable actions. These models represent desires as simple associations between agents and world states. In this paper we show that by representing desires as probabilistic programs, an inverse planning model can infer complex desires underlying complex behaviors—desires with temporal and logical structure, which can be fulfilled in different ways. Our model, which combines basic desires via logical primitives, is inspired by recent probabilistic grammarbased models of concept learning. Through an experiment where we vary behaviors parametrically, we show that our model predicts with high accuracy how people infer complex desires. Our work sheds light on the representations underlying mental states, and paves the way towards algorithms that can reason about others’ minds as we do.