Wanting to be Understood

2025-04-09

AI Summary

This work investigates whether humans possess an intrinsic motivation to be understood by others—and how this motivation synergizes with the motivation to understand others. Method: Grounded in the active inference framework, we formally model “being understood” as a tripartite intrinsic reward comprising imitability, influenceability, and sub-reactive-time prediction, and integrate it into a multi-agent reinforcement learning architecture enabling bidirectional understanding-driven agency. Our approach synthesizes artificial curiosity, influence modeling, and anticipatory behavioral prediction to simulate perceptually coupled social interaction without extrinsic rewards. Contribution/Results: The intrinsic motivation alone suffices to spontaneously generate stable, reciprocal interactions; in unilateral extrinsic-reward tasks, collaboration success rates increase significantly. These findings establish reciprocal understanding as an endogenous driver of social cooperation and introduce a novel paradigm for computational modeling of social cognition.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Economics, Online Markets and Human Computation: Social networks and social learning
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

This paper explores an intrinsic motivation for mutual awareness, hypothesizing that humans possess a fundamental drive to understand extit{and to be understood} even in the absence of extrinsic rewards. Through simulations of the perceptual crossing paradigm, we explore the effect of various internal reward functions in reinforcement learning agents. The drive to understand is implemented as an active inference type artificial curiosity reward, whereas the drive to be understood is implemented through intrinsic rewards for imitation, influence/impressionability, and sub-reaction time anticipation of the other. Results indicate that while artificial curiosity alone does not lead to a preference for social interaction, rewards emphasizing reciprocal understanding successfully drive agents to prioritize interaction. We demonstrate that this intrinsic motivation can facilitate cooperation in tasks where only one agent receives extrinsic reward for the behaviour of the other.

Problem

• Explores intrinsic motivation for mutual understanding in humans
• Tests reward functions in RL agents for social interaction
• Demonstrates how reciprocal understanding drives cooperation

Innovation

• Active inference artificial curiosity reward
• Intrinsic rewards for imitation and influence
• Sub-reaction time anticipation mechanism