Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution
Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution
复制标题
DOI：
--
复制
发表时间：
2011
影响因子：
2.5
通讯作者：
Chris L. Baker;R. Saxe;J. Tenenbaum
中科院分区：
文献类型：
--
作者：
Chris L. Baker;R. Saxe;J. Tenenbaum
贝叶斯心理理论：联合信念-欲望归因建模。贝克（clbaker@mit.edu）丽贝卡R.萨克斯（saxe@mit.edu）约书亚B. Tenenbaum（jbt@mit.edu）Department of Brain and Cognitive Sciences，MIT剑桥，MA 02139摘要我们提出了一个理解心智理论（The- ory of Mind，ToM）的计算框架：人类推理主体的心理状态（如信念和欲望）的能力。我们的贝叶斯模型的ToM（或BToM）表达的信念和欲望依赖的行动在ToM的心脏作为一个部分可观察的马尔可夫决策过程（POMDP）的预测模型，并重建一个代理的联合信念状态和奖励功能，使用贝叶斯推理，条件下观察代理的行为在一些环境背景下。我们测试BToM的参与者序列的代理移动在简单的空间场景，并要求联合推理的代理人的愿望和信仰的未观察到的方面的环境。BToM的性能大大优于两个更简单的变体：一个是在不参考代理的信念的情况下推断出欲望，另一个是在不参考代理在环境中的动态观察的情况下推断出信念。保留字：心理理论;社会认知;行动理解;贝叶斯推理;部分可观测马尔可夫决策过程引言人类社会行为的核心是心理理论（ToM），解释和预测人们在不可观测的心理状态（如信念和欲望）方面可观测行为的能力。以哈罗德为例，他在一个星期天早上离开宿舍去了学校图书馆。当他伸手去打开图书馆的前门时，他会发现它是锁着的--星期天关门。我们怎么解释他的行为？他想要一本书，他相信他想要的书在图书馆，而且他还相信（事实证明是错误的）图书馆在星期天开放，这似乎是可信的。这种对行为的心理状态解释很好地脱离了可观察的数据，导致了一个从根本上说是不适定的推理问题。信念和欲望的许多不同组合可以解释同一行为，关于信念和欲望的强度的推断相互权衡，相对概率受到上下文的严重影响。也许哈罗德几乎肯定图书馆会关闭，但他非常需要一本书，所以他仍然愿意穿过校园，万一它会开放。如果哈罗德在星期六午夜发现图书馆锁着，而不是在星期二中午，这个解释似乎更有可能。如果他在几个小时后到达，手里已经拿着一本明天到期的书，那么他可能知道图书馆关门了，并不想买新书，而只是想把以前借过的书还到夜间投书箱。几位作者最近提出了人们如何推断他人目标或偏好的模型，作为一种贝叶斯逆规划或逆决策理论（Baker，Saxe，& Tenenbaum，2009; Feldman & Tremoulet，2008; Lucas，Grif fiths，Xu，&福塞特，2009;卑尔根，Evans，& Tenenbaum，2010; Yoshida，Dolan，& Friston，2008; Ullman等人，2010年）。这些模型采用了控制理论、计量经济学和博弈论的工具，以形式化儿童和成人意向代理概念核心的理性行动原则（German，N 'adasdy，Csibra，& Bir' o，1995; Dennett，1987）：在其他条件相同的情况下，代理人被期望选择尽可能有效和高效地实现其愿望的行动，即，以最大化其预期效用。目标或偏好，然后推断的基础上，观察到的行动最直接最大化的目标或效用函数。心理理论通过整合表征性心理状态（如关于世界的主观信念），超越了对意向性主体的目标和偏好的认识（Perner，1991）。特别是，对错误信念进行推理的能力已经被用来区分心理理论和非表征的有意行为理论（维默和佩纳，1983;大西和巴亚尔金，2005）。本文的目标是在贝叶斯框架内对人类心理理论进行建模.受逆向规划模型的启发，我们将贝叶斯ToM（Bayesian ToM，BToM）问题转化为逆向规划和推理问题，将智能体对世界的规划和推理表示为部分可观测的马尔可夫决策过程（POMDP），并利用贝叶斯推理对该正向模型进行反演。重要的是，这个模型包括代理人的愿望（作为一个效用函数）和代理人自己对环境的主观信念（作为一个概率分布），这可能是不确定的，可能与现实不同。我们在一个实验中定量地测试了这个模型的预测，在这个实验中，人们必须同时判断在简单的空间环境中移动的代理人的信念和愿望，在不完全或不完善的知识。我们工作的重要先驱是几个计算模型（Goodman等人，二○ ○六年; Bello & Cassimilar，2006; Goodman，Baker，& Tenenbaum，2009）和发展心理学家的非正式理论建议（Wellman，1990; Gopnik & Meltzoff，1997; German & Csibra，2003）。Goodman等人（2006年）在经典的“错误信念”任务中模拟了信念和欲望推断如何相互作用，该任务用于评估儿童的心理理论推理（维默和佩纳，1983年）。该模型将图1（a）中所示的模式实例化为具有几个心理学上可解释的因果贝叶斯网络，
Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution Chris L. Baker (clbaker@mit.edu) Rebecca R. Saxe (saxe@mit.edu) Joshua B. Tenenbaum (jbt@mit.edu) Department of Brain and Cognitive Sciences, MIT Cambridge, MA 02139 Abstract We present a computational framework for understanding The- ory of Mind (ToM): the human capacity for reasoning about agents’ mental states such as beliefs and desires. Our Bayesian model of ToM (or BToM) expresses the predictive model of belief- and desire-dependent action at the heart of ToM as a partially observable Markov decision process (POMDP), and reconstructs an agent’s joint belief state and reward func- tion using Bayesian inference, conditioned on observations of the agent’s behavior in some environmental context. We test BToM by showing participants sequences of agents moving in simple spatial scenarios and asking for joint inferences about the agents’ desires and beliefs about unobserved aspects of the environment. BToM performs substantially better than two simpler variants: one in which desires are inferred without ref- erence to an agent’s beliefs, and another in which beliefs are inferred without reference to the agent’s dynamic observations in the environment. Keywords: Theory of mind; Social cognition; Action un- derstanding; Bayesian inference; Partially Observable Markov Decision Processes Introduction Central to human social behavior is a theory of mind (ToM), the capacity to explain and predict people’s observable ac- tions in terms of unobservable mental states such as beliefs and desires. Consider the case of Harold, who leaves his dorm room one Sunday morning for the campus library. When he reaches to open the library’s front door he will find that it is locked – closed on Sunday. How can we explain his behav- ior? It seems plausible that he wants to get a book, that he believes the book he wants is at the library, and that he also believes (falsely, it turns out) that the library is open on Sun- day. Such mental state explanations for behavior go well be- yond the observable data, leading to an inference problem that is fundamentally ill-posed. Many different combinations of beliefs and desires could explain the same behavior, with inferences about the strengths of beliefs and desires trading off against each other, and relative probabilities modulated heavily by context. Perhaps Harold is almost positive that the library will be closed, but he needs a certain book so badly that he still is willing to go all the way across campus on the off chance it will be open. This explanation seems more prob- able if Harold shows up to find the library locked on Saturday at midnight, as opposed to noon on Tuesday. If he arrives after hours already holding a book with a due date of tomor- row, it is plausible that he knows the library is closed and is seeking not to get a new book, but merely to return a book checked out previously to the night drop box. Several authors have recently proposed models for how people infer others’ goals or preferences as a kind of Bayesian inverse planning or inverse decision theory (Baker, Saxe, & Tenenbaum, 2009; Feldman & Tremoulet, 2008; Lucas, Grif- fiths, Xu, & Fawcett, 2009; Bergen, Evans, & Tenenbaum, 2010; Yoshida, Dolan, & Friston, 2008; Ullman et al., 2010). These models adapt tools from control theory, econometrics and game theory to formalize the principle of rational ac- tion at the heart of children and adults’ concept of intentional agency (Gergely, N´adasdy, Csibra, & Bir´o, 1995; Dennett, 1987): all else being equal, agents are expected to choose ac- tions that achieve their desires as effectively and efficiently as possible, i.e., to maximize their expected utility. Goals or preferences are then inferred based on which objective or utility function the observed actions maximize most directly. ToM transcends knowledge of intentional agents’ goals and preferences by incorporating representational mental states such as subjective beliefs about the world (Perner, 1991). In particular, the ability to reason about false beliefs has been used to distinguish ToM from non-representational theories of intentional action (Wimmer & Perner, 1983; Onishi & Baillargeon, 2005). Our goal in this paper is to model hu- man ToM within a Bayesian framework. Inspired by mod- els of inverse planning, we cast Bayesian ToM (BToM) as a problem of inverse planning and inference, representing an agent’s planning and inference about the world as a partially observable Markov decision process (POMDP), and invert- ing this forward model using Bayesian inference. Critically, this model includes representations of both the agent’s de- sires (as a utility function), and the agent’s own subjective beliefs about the environment (as a probability distribution), which may be uncertain and may differ from reality. We test the predictions of this model quantitatively in an experiment where people must simultaneously judge beliefs and desires for agents moving in simple spatial environments under in- complete or imperfect knowledge. Important precursors to our work are several computational models (Goodman et al., 2006; Bello & Cassimatis, 2006; Goodman, Baker, & Tenenbaum, 2009) and informal theo- retical proposals by developmental psychologists (Wellman, 1990; Gopnik & Meltzoff, 1997; Gergely & Csibra, 2003). Goodman et al. (2006) model how belief and desire infer- ences interact in the classic “false belief” task used to assess ToM reasoning in children (Wimmer & Perner, 1983). This model instantiates the schema shown in Fig. 1(a) as a causal Bayesian network with several psychologically interpretable,