Help or Hinder: Bayesian Models of Social Goal Inference

Abstract

Everyday social interactions are heavily influenced by our snap judgments about
\nothers’ goals. Even young infants can infer the goals of intentional agents from
\nobserving how they interact with objects and other agents in their environment:
\ne.g., that one agent is ‘helping’ or ‘hindering’ another’s attempt to get up a hill
\nor open a box. We propose a model for how people can infer these social goals
\nfrom actions, based on inverse planning in multiagent Markov decision problems
\n(MDPs). The model infers the goal most likely to be driving an agent’s behavior
\nby assuming the agent acts approximately rationally given environmental constraints
\nand its model of other agents present. We also present behavioral evidence
\nin support of this model over a simpler, perceptual cue-based alternative.