EconPapers    
Economics at your fingertips  
 

Perceptual interventions ameliorate statistical discrimination in learning agents

Edgar A. Duéñez-Guzmán (), Ramona Comanescu, Yiran Mao, Kevin R. McKee, Ben Coppin, Suzanne Sadedin, Silvia Chiappa, Alexander S. Vezhnevets, Michiel A. Bakker, Yoram Bachrach, William Isaac, Karl Tuyls and Joel Z. Leibo
Additional contact information
Edgar A. Duéñez-Guzmán: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Ramona Comanescu: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Yiran Mao: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Kevin R. McKee: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Ben Coppin: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Suzanne Sadedin: b Independent researcher , London N1C 4DN , United Kingdom
Silvia Chiappa: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Alexander S. Vezhnevets: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Michiel A. Bakker: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Yoram Bachrach: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
William Isaac: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Karl Tuyls: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom
Joel Z. Leibo: a Google DeepMind, Google UK Ltd. , London EC4A 3TW , United Kingdom

Proceedings of the National Academy of Sciences, 2025, vol. 122, issue 25, e2319933121

Abstract:

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 information-processing limits, potentially increasing or decreasing undesired biases. Here, we use game theory and multiagent reinforcement learning to investigate how undesired biases emerge, and how a 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.

Keywords: statistical discrimination; reinforcement learning; partner choice; perceptual interventions (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1073/pnas.2319933121 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nas:journl:v:122:y:2025:p:e2319933121

Access Statistics for this article

More articles in Proceedings of the National Academy of Sciences from Proceedings of the National Academy of Sciences
Bibliographic data for series maintained by PNAS Product Team ().

 
Page updated 2025-06-25
Handle: RePEc:nas:journl:v:122:y:2025:p:e2319933121