The prominence of Bayesian modeling of cognition has increased recently largely because
of mathematical advances in specifying and deriving predictions from complex probabilistic …

We present a computational framework for understanding Theory of Mind (ToM): the human
capacity for reasoning about agents' mental states such as beliefs and desires. Our …

Robots can learn the right reward function by querying a human expert. Existing approaches
attempt to choose questions where the robot is most uncertain about the human's response; …

Plan recognition, activity recognition, and intent recognition together combine and unify
techniques from user modeling, machine vision, intelligent user interfaces, human/computer …

This chapter first explains what intuitive theories are, how they can be modeled as
probabilistic, generative programs, and how intuitive theories support various cognitive …

Reward functions are a common way to specify the objective of a robot. As designing reward
functions can be extremely challenging, a more promising approach is to directly learn …

From early childhood, human beings learn not only from collections of facts about the world
but also from social contexts through observations of other people, communication, and …

Theory of mind, the capacity to understand and ascribe mental states, has traditionally been
conceptualized as analogous to a scientific theory. However, recent work in philosophy and …

Recent work has shown that young children can learn about preferences by observing the
choices and emotional reactions of other people, but there is no unified account of how this …

Bayesian approaches to utility elicitation typically adopt (myopic) expected value of
information (EVOI) as a natural criterion for selecting queries. However, EVOI-optimization is …