Learning Theory of Mind via Dynamic Traits Attribution

TL;DR

This paper introduces a neural Theory of Mind architecture that learns latent character traits from past actions to improve social prediction and understanding in agents, inspired by human trait inference.

Contribution

It proposes a novel neural ToM model using dynamic trait vectors and fast weights, enhancing mental state inference and social behavior prediction.

Findings

Improved prediction of agent behavior using trait-based modulation.

Enhanced performance in indirect false-belief understanding tasks.

Better social assistance behaviors in experiments.

Abstract

Machine learning of Theory of Mind (ToM) is essential to build social agents that co-live with humans and other agents. This capacity, once acquired, will help machines infer the mental states of others from observed contextual action trajectories, enabling future prediction of goals, intention, actions and successor representations. The underlying mechanism for such a prediction remains unclear, however. Inspired by the observation that humans often infer the character traits of others, then use it to explain behaviour, we propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories. This trait vector then multiplicatively modulates the prediction mechanism via a `fast weights' scheme in the prediction neural network, which reads the current context and predicts the behaviour. We empirically show that the fast weights provide a good inductive bias to model the character traits of agents and hence improves mindreading ability. On the indirect assessment of false-belief understanding, the new ToM model enables more efficient helping behaviours.