Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution

By Chris L. Baker, Rebecca Saxe, Josh Tenenbaum. 2011

350 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Theory of Mind: A Neural Prediction Problem (2013, positive): “Like vision, theory of mind can be understood as an inverse problem (Baker et al., 2011; Baker et al., 2009); the challenge is to use the observable evidence (in this case human behaviors and states) to infer the invisible causal structure that gave rise to the evidence (the goals, thoughts, and…”
Machine Theory of Mind (2018, methodology): “, 2000; Abbeel & Ng, 2004), Bayesian Theory of Mind (Baker et al., 2011; Jara-Ettinger et al., 2016) or game theory (Yoshida et al.”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, methodology): “We would also like to investigate fast online adaptation [1, 20] and the relationship to computational Theory of Mind [104, 4], as well as generalized (transferable) oracles over similar opponent policies using successor features [6].”
Learning the Preferences of Ignorant, Inconsistent Agents (2015, background): “The problem of learning a person’s preferences from observations of their choices features prominently in economics (Hausman 2011), in cognitive science (Baker, Saxe, and Tenenbaum 2011; Ullman et al. 2009), and in applied machine learning (Jannach et al. 2010; Ermon et al. 2014).”
The role of prediction in social neuroscience (2012, background): “A recent predictive model of theory of mind has been proposed by Baker et al. (2011), which relies on Bayesian inferential statistics to model belief and goal-dependent action, which is mediated by the state of the environment and perceptual access to the belief state, and by general knowledge of…”
Intuitive Theories (2020, background): “Consider the scenario depicted in Figure 10 (cf. Baker et al., 2011).”
Algorithms for the Greater Good! On Mental Modeling and Acceptable Symbiosis in Human-AI Collaboration (2018, methodology): “Recent approaches such as the Bayesian Theory of Mind (Baker, Saxe, and Tenenbaum 2011; Lake et al. ), takes a probabilistic approach to the problem.”
Theory of Mind and Preference Learning at the Interface of Cognitive Science, Neuroscience, and AI: A Review (2022, methodology): “…to varying degrees in this review, but detailed reviews for each are provided in the following papers (Game ToM in Yoshida et al., 2008; Observational Reinforcement Learning in Albrecht and Stone, 2018; Inverse Reinforcement Learning in Arora and Doshi, 2021 and Bayesian ToM in Baker et al., 2011).”
Reasoning about reasoning by nested conditioning: Modeling theory of mind with probabilistic programs (2014, unknown): “Most directly, we build on the Bayesian approach to theory of mind [2, 3], which takes the principle of rational action to be central to the concept of intentional agency: all else being equal, agents are expected to choose actions that satisfy their goals as effectively as possible.”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “prediction [106]; 2 discovery of the invisible attractive/repulsive fields of objects and recognizing their functions by analyzing human trajectories [72]; 3 understanding of scenes by function and activity [25], where the attraction fields are longer range in a scene than the functionality maps [27”
Autonomous agents modelling other agents: A comprehensive survey and open problems (2017, background): “In subsequent work, both Baker et al. (2011) and Ramırez and Geffner (2011) propose planning-based methods to infer the goals (and beliefs) of an agent in partially observable MDPs (Kaelbling et al., 1998).”
A decision network account of reasoning about other people's choices. (2015, background): “…to model situations in which an agent navigates through a state space and chooses an action in each state (Baker & Tenenbaum, 2014; Baker et al., 2008; Baker et al., 2009, 2011; Doshi et al., 2010; Jara-Ettinger et al., 2012; Pynadath & Marsella, 2005; Tauber & Steyvers, 2011; Ullman et al., 2009).”
Who is Mistaken? (2016, background): “[3] propose a Bayesian model for learning beliefs based on a partially-observable Markov Decision Process.”