# Theory of Minds: Understanding Behavior in Groups Through Inverse Planning

## TL;DR

This paper introduces a probabilistic model for understanding multi-agent social behavior by inferring latent relationships, enabling rapid and human-like reasoning about group dynamics from limited observations.

## Contribution

It proposes a novel generative model using Composable Team Hierarchies for inferring hidden relationships in multi-agent interactions, grounded in stochastic game formalism.

## Key findings

- The algorithm accurately infers underlying agent relationships from sparse data.
- It predicts future actions of agents in group settings.
- The inference patterns align closely with human judgments.

## Abstract

Human social behavior is structured by relationships. We form teams, groups, tribes, and alliances at all scales of human life. These structures guide multi-agent cooperation and competition, but when we observe others these underlying relationships are typically unobservable and hence must be inferred. Humans make these inferences intuitively and flexibly, often making rapid generalizations about the latent relationships that underlie behavior from just sparse and noisy observations. Rapid and accurate inferences are important for determining who to cooperate with, who to compete with, and how to cooperate in order to compete. Towards the goal of building machine-learning algorithms with human-like social intelligence, we develop a generative model of multi-agent action understanding based on a novel representation for these latent relationships called Composable Team Hierarchies (CTH). This representation is grounded in the formalism of stochastic games and multi-agent reinforcement learning. We use CTH as a target for Bayesian inference yielding a new algorithm for understanding behavior in groups that can both infer hidden relationships as well as predict future actions for multiple agents interacting together. Our algorithm rapidly recovers an underlying causal model of how agents relate in spatial stochastic games from just a few observations. The patterns of inference made by this algorithm closely correspond with human judgments and the algorithm makes the same rapid generalizations that people do.