Social coordination perpetuates stereotypic expectations and behaviors across generations in deep multi-agent reinforcement learning

TL;DR

This paper demonstrates how social coordination dynamics in multi-agent reinforcement learning can create and reinforce stereotypes through feedback loops, independent of biased motivations, with implications for understanding stereotype persistence.

Contribution

It introduces a computational model showing how expectations in social coordination lead to stereotype formation and confirms human behavior exhibits similar feedback loops, highlighting a non-motivational basis.

Findings

Feedback loops in social coordination can produce stereotypes.

Human behavior aligns with the model's feedback mechanism.

Stereotype persistence does not require biased motivations.

Abstract

Despite often being perceived as morally objectionable, stereotypes are a common feature of social groups, a phenomenon that has often been attributed to biased motivations or limits on the ability to process information. We argue that one reason for this continued prevalence is that pre-existing expectations about how others will behave, in the context of social coordination, can change the behaviors of one's social partners, creating the very stereotype one expected to see, even in the absence of other potential sources of stereotyping. We use a computational model of dynamic social coordination to illustrate how this "feedback loop" can emerge, engendering and entrenching stereotypic behavior, and then show that human behavior on the task generates a comparable feedback loop. Notably, people's choices on the task are not related to social dominance or system justification, suggesting biased motivations are not necessary to maintain these stereotypes.