Teaching Social Behavior through Human Reinforcement for Ad hoc Teamwork -The STAR Framework

TL;DR

This paper introduces the STAR framework, a method for teaching autonomous agents to adhere to human social norms within ad hoc teams through human feedback, addressing the challenge of learning complex, non-predefined social behaviors.

Contribution

The paper proposes the STAR framework, enabling multiagent teams to learn social norms via human reinforcement, advancing beyond rule-based approaches to more flexible, norm-based social behavior learning.

Findings

Agents learn to avoid socially unacceptable actions through human feedback.

The STAR framework improves agents' social compliance in team settings.

Demonstrates effective norm adherence in mixed human-agent teams.

Abstract

As AI technology continues to develop, more and more agents will become capable of long term autonomy alongside people. Thus, a recent line of research has studied the problem of teaching autonomous agents the concept of ethics and human social norms. Most existing work considers the case of an individual agent attempting to learn a predefined set of rules. In reality, however, social norms are not always pre-defined and are very difficult to represent algorithmically. Moreover, the basic idea behind the social norms concept is ensuring that one's actions do not negatively influence others' utilities, which is inherently a multiagent concept. Thus, here we investigate a way to teach agents, as a team, how to act according to human social norms. In this research, we introduce the STAR framework used to teach an ad hoc team of agents to act in accordance with human social norms. Using a hybrid team (agents and people), when taking an action considered to be socially unacceptable, the agents receive negative feedback from the human teammate(s) who has(have) an awareness of the team's norms. We view STAR as an important step towards teaching agents to act more consistently with respect to human morality.