Strategic Shaping of Human Prosociality: A Latent-State POMDP Framework

TL;DR

This paper introduces a decision-theoretic framework where robots strategically influence human prosociality during interactions by modeling it as a latent state and optimizing actions to enhance cooperation.

Contribution

It presents a novel latent-state POMDP model for shaping human prosociality, integrating learning and influence strategies for improved human-robot collaboration.

Findings

The learned policy outperforms baseline strategies in team performance.

The model effectively increases observed human cooperative behavior.

The framework successfully infers and influences human prosocial states.

Abstract

We propose a decision-theoretic framework in which a robot strategically can shape inferred human's prosocial state during repeated interactions. Modeling the human's prosociality as a latent state that evolves over time, the robot learns to infer and influence this state through its own actions, including helping and signaling. We formalize this as a latent-state POMDP with limited observations and learn the transition and observation dynamics using expectation maximization. The resulting belief-based policy balances task and social objectives, selecting actions that maximize long-term cooperative outcomes. We evaluate the model using data from user studies and show that the learned policy outperforms baseline strategies in both team performance and increasing observed human cooperative behavior.