The Naïve Utility Calculus: Computational Principles Underlying Commonsense Psychology.

382 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.

Machine Theory of Mind (2018, background): “…RL (Ng et al., 2000; Abbeel & Ng, 2004), Bayesian inference (Lucas et al., 2014; Evans et al., 2016), Bayesian Theory of Mind (Baker et al., 2011; Jara-Ettinger et al., 2016; Baker et al., 2017) or game theory (Camerer et al., 2004; Yoshida et al., 2008; Camerer, 2010; Lanctot et al., 2017).”
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.”
What's worth the effort: Ten-month-old infants infer the value of goals from the costs of actions (2017, positive): “…infants’ performance requires a mental model both of how agents work in the forward direction (in accord with a principle of maximizing utilities; Jara-Ettinger et al., 2016) and a procedure for inverting this model (in accord with the computational framework of inverse planning; Baker et al.,…”
Theory of mind as inverse reinforcement learning (2019, background): “Beyond inverse reinforcement learning Human intuitive theories are often approximations of the phenomena they aim to explain [5,67], allowing us to ignore complexities that are less useful for prediction and explanation, much in the same way that scientific theories gain explanatory power through ab”