Reasoning about reasoning by nested conditioning: Modeling theory of mind with probabilistic programs

By Andreas Stuhlmüller, Noah D. Goodman. 2014

63 citations recorded by the source corpus.

A wide range of human reasoning patterns can be explained as conditioning in probabilistic models; however, conditioning has traditionally been viewed as an operation applied to such models, not represented in such models. We describe how probabilistic programs can explicitly represent conditioning as part of a model. This enables us to describe reasoning about others' reasoning using nested conditioning. Much of human reasoning is about the beliefs, desires, and intentions of other people; we use probabilistic programs to formalize these inferences in a way that captures the flexibility and inherent uncertainty of reasoning about other agents. We express examples from game theory, artificial intelligence, and linguistics as recursive probabilistic programs and illustrate how this representation language makes it easy to explore new directions in each of these fields. We discuss the algorithmic challenges posed by these kinds of models and describe how dynamic programming techniques can help address these challenges.

Subfields: Artificial Intelligence, Probabilistic & Bayesian Methods, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Probabilistic & Bayesian Methods

In Cognitive Science & Psychology

Citations in the corpus

An Introduction to Probabilistic Programming (2018, background): “Goodman and his colleagues highlight many such models for agent interactions that capture agents’ knowledge about other agents (Stuhlmüller and Goodman, 2014) and many source code examples are available online (Stuhlmüller, 2014).”
Learning physics from dynamical scenes (2014, background): “Probabilistic programs are useful for representing knowledge with uncertainty (e.g. Stuhlmüller & Goodman, 2013).”
Nesting Probabilistic Programs (2018, background): “One enticing manner they do this is by allowing arbitrary nesting of models, known in the probabilistic programming literature as queries [7], such that it is easy to define and run nested inference problems [7, 15, 21, 26].”
Rational quantitative attribution of beliefs, desires and percepts in human mentalizing (2017, background): “Extending these models to capture (as BToM requires) agents’ subjective beliefs about the world, and nested beliefs about other agents’ beliefs 50,51 , is an important direction for future research.”
Concepts in a Probabilistic Language of Thought (2014, methodology): “The pattern of using an embedded query to capture the choices of another agent is a very general pattern for modeling intuitive psychology (Stuhlmüller & Goodman, 2013).”