Perceptual interventions ameliorate statistical discrimination in learning agents

• 成果类型: Article
• 署名作者: Duenez-Guzman, Edgar A.; Comanescu, Ramona; Mao, Yiran; Mckee, Kevin R.; Coppin, Ben; Sadedin, Suzanne; Chiappa, Silvia; Vezhnevets, Alexander S.; Bakker, MichielA.; Bachrach, Yoram; Isaac, William; Tuyls, Karl; Leibo, Joel Z.
• 署名单位: Alphabet Inc.; Google Incorporated; DeepMind
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-12204
• DOI: 10.1073/pnas.2319933121
• 发表日期: 2025-06-24
• 关键词: partner choice; reinforcement; COOPERATION; ECONOMICS; LEVEL; RECIPROCITY; PREJUDICE; selection; cognition; systems

摘要

Choosing social partners is a potentially demanding task which involves paying attention to the right information while disregarding salient but possibly irrelevant features. The resultant trade-off between cost of evaluation and quality of decisions can lead to undesired bias. Information-processing abilities mediate this trade-off, where individuals with higher ability choose better partners leading to higher performance. By altering the salience of features, technology can modulate the effect of informationprocessing limits, potentially increasing or decreasing undesired biases. Here, we use game theory and multiagent reinforcement learning to investigate how undesired biases emerge, and howa technological layer (in the form of a perceptual intervention) between individuals and their environment can ameliorate such biases. Our results show that a perceptual intervention designed to increase the salience of outcome-relevant features can reduce bias in agents making partner choice decisions. Individuals learning with a perceptual intervention showed less bias due to decreased reliance on features that only spuriously correlate with behavior. Mechanistically, the perceptual intervention effectively increased the information-processing abilities of the individuals. Our results highlight the benefit of using multiagent reinforcement learning to model theoretically grounded social behaviors, particularly when real-world complexity prohibits fully analytical approaches.