Theory of mind as inverse reinforcement learning

By Julian Jara-Ettinger. Current Opinion in Behavioral Sciences, 2019

211 citations recorded by the source corpus.

We review the idea that Theory of Mind—our ability to reason about other people's mental states—can be formalized as inverse reinforcement learning. Under this framework, expectations about how mental states produce behavior are captured in a reinforcement learning (RL) model. Predicting other people’s actions is achieved by simulating a RL model with the hypothesized beliefs and desires, while mental-state inference is achieved by inverting this model. Although many advances in inverse reinforcement learning (IRL) did not have human Theory of Mind in mind, here we focus on what they reveal when conceptualized as cognitive theories. We discuss landmark successes of IRL, and key challenges in building human-like Theory of Mind.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Developmental and Educational Psychology

View Paper: https://www.semanticscholar.org/paper/83ea160705df83de95485d385b210effa269925a

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 Cognitive Neuroscience

In Developmental and Educational Psychology

Citations in the corpus

Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks (2023, background): “In fact, there are already many reasonable computational models that try to directly capture this ability (e.g. 31; 32; 33; 34; 35; 10), and which put formal skin on decades-old proposals in cognitive science and psychology.”
MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks (2021, methodology): “As a first step to address this question, this paper explores theory of mind modeling (Chandrasekaran et al., 2017; Rabinowitz et al., 2018; Jara-Ettinger, 2019) in situated language communication (Iwahashi et al.”
Theory of Mind and Preference Learning at the Interface of Cognitive Science, Neuroscience, and AI: A Review (2022, background): “, in the fields of Inverse Reinforcement Learning—IRL—and Preference Learning), and it has been shown that ToM can indeed be cast as an IRL problem (Jara-Ettinger, 2019).”