Help or Hinder: Bayesian Models of Social Goal Inference

By Tomer D. Ullman, Chris L. Baker, Owen Macindoe, Owain Evans, Noah D. Goodman, Josh Tenenbaum. 2009

214 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

Machine Theory of Mind (2018, background): “Third, there are many other dimensions over which we may wish to characterise agents, such as whether they are animate or inanimate (Scholl & Tremoulet, 2000), prosocial or adversarial (Ullman et al., 2009), reactive or able to plan (Sutton & Barto, 1998).”
Knowledge and implicature: Modeling language understanding as social cognition (2012, methodology): “So far, nothing in the model is unique to language—indeed, similar models have been used to model social cognition more generally (Baker, Saxe, & Tenenbaum, 2009; Goodman, Baker, & Tenenbaum, 2009; Ullman et al., 2009).”
How Robot Verbal Feedback Can Improve Team Performance in Human-Robot Task Collaborations (2015, background): “There has also been extensive work on intent recognition relying on perspective taking or Theory of Mind-inspired models to allow a robot to recognize a person’s intentional behavior through observation [4], as well as to recognize and generate intentional face-to-face meeting initiation behavior [9”
Coordinate to cooperate or compete: Abstract goals and joint intentions in social interaction (2016, background): “Young children and even infants make inferences about socially positive actions and people that are consistent with inference over recursive utility functions: being helpful can be understood as one agent taking another agent’s utility function into account in their own decision (Kiley Hamlin, Ullma”
Using Inverse Planning and Theory of Mind for Social Goal Inference (2011, background): “‖ This phenomenon is sometimes referred to as the perception of animacy (for a technical description see Feldman and Tremoulet, 2008) Modern research that employed the perceived animacy phenomenon showed that not only did human observers perceive that the agents had goals; they also appeared to perc”
Modeling Interaction via the Principle of Maximum Causal Entropy (2010, background): “Modeling the interactions of multiple agents is an important task for uncovering the motives of negotiating parties, planning a robot’s movement in a crowded environment, and assessing the perceived roles of interacting agents (Ullman et al., 2009).”
The mentalistic basis of core social cognition: experiments in preverbal infants and a computational model. (2013, unknown): “A crucial aspect of the Inverse Planning approach is that it can account for different social judgments about the exact same actions, depending on the beliefs, knowledge, and goals of the agents involved (Ullman et al. 2010); a cue-based approach cannot explain how a perceptually indistinguishable a”
Bayesian Theory of Mind: Modeling Joint Belief-Desire Attribution (2011, background): “Several authors have recently proposed models for how people infer others’ goals or preferences as a kind of Bayesian inverse planning or inverse decision theory (Baker, Saxe, & Tenenbaum, 2009; Feldman & Tremoulet, 2008; Lucas, Griffiths, Xu, & Fawcett, 2009; Bergen, Evans, & Tenenbaum, 2010; Yoshi”
A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress (2018, background): “[8] demonstrate the inference of a human’s goal as an inverse planning problem in an MDP.”
On the nature and origin of intuitive theories : learning, physics and psychology (2015, background): “As I mentioned, there is an ongoing discussion whether cues alone could account for this kind of reasoning, but since cues are unlikely as a sole-explanation even within each domain [186, 12] it is doubtful”
Intuitive Theories (2020, methodology): “Further experiments motivated by the inverse planning approach have shown that people are sensitive to configurations of the environment when inferring one agents' social goals of avoiding/approaching (Baker, Goodman, & Tenenbaum, 2008). or helping/hindering another agent (Ullman et al., 2009).”
A decision network account of reasoning about other people's choices. (2015, background): “Tenenbaum, 2008; Baker et al., 2009, Baker, Saxe, & Tenenbaum, 2011; Doshi, Qu, Goodie, & Young, 2010; Goodman et al., 2009; Jara-Ettinger, Baker, & Tenenbaum, 2012; Pantelis et al., 2014; Pynadath & Marsella, 2005; Tauber & Steyvers, 2011; Ullman et al., 2009).”
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).”