Rational quantitative attribution of beliefs, desires and percepts in human mentalizing

By Chris L. Baker, Julian Jara-Ettinger, Rebecca Saxe, Josh Tenenbaum. 2017

540 citations recorded by the source corpus.

Subfields: Developmental and Educational Psychology, Social Psychology, Sociology and Political Science, 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 Developmental and Educational Psychology

In Social Psychology

In Sociology and Political Science

In Cognitive Science & Psychology

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, methodology): “” One alternative to a cue-based account is to use generative models of action choice, as in the Bayesian inverse planning, or Bayesian theory of mind (ToM), models of Baker et al. (2009) or the naive utility calculus models of Jara-Ettinger et al. (2015) (see also Jern and Kemp [2015] and Tauber an”
Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning (2019, background): “Furthermore, humans are both able to interpret the actions of others and can act in a way that is informative when their actions are being observed by others, capabilities that are commonly called theory of Mind (ToM), (Baker et al., 2017).”
Machine Theory of Mind (2018, methodology): “…2000; Ramachandran & Amir, 2007; Ziebart et al., 2008; Boularias et al., 2011), or Bayesian ToM (e.g. Baker et al., 2011; Nakahashi et al., 2016; Baker et al., 2017), we drive the ToMnet to amortise its inference through neural networks (as in Kingma & Welling, 2013; Rezende et al., 2014; Ho &…”
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning (2018, background): “This process is closely related to the kind of theory of mind reasoning that humans routinely undertake (Baker et al., 2017).”
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration (2020, background): “humans’ goals by observing their actions (Baker et al., 2017; Ullman et al., 2009; Rabinowitz et al., 2018; Shum et al., 2019).”
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.”
Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems (2022, background): “It has been demonstrated that humans, during an interaction, can reason about others’ ideas, goals, intentions and predict partners’ behaviors, a capability called Theory of Mind (ToM) [10, 127, 163].”
Theory of mind as inverse reinforcement learning (2019, background): “Yet, deep IRL with the flexibility of more traditional IRL models [17,53] remains distant [13].”