mlsanityData to 7 Oct 2026

Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics

arXiv 2607.19389 ↗First posted 2 Jul 2026cs.CY cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

As AI-driven Decision Makers (ADMs) influence our socioeconomic reality, their roles in both enhancing efficiency and amplifying the social biases have drawn significant attention. In this paper, we revisit the nuances of long-term fairness achievable by an ADM-- specifically, through the lens of a loan approver inducing a population-level wealth dynamics. The literature generally (a) considers passive environments, i.e. the decisions of an ADM does not change the population's behaviour, and (b) measures bias in terms of disparity in the instantaneous decisions rather than downstream equity. Modern ADMs challenge both the notions. To address these caveats, we first formalise the wealth dynamics induced by a loan approving ADM interacting with a multi-demographic population as a Performative Markov Decision Process. Then, we mitigate the absence of such a performative test-bed by developing Eutopia: a lending-process simulator enabled with a novel performative data generator to learn long-term fair strategies. With Eutopia, we test reinforcement learning algorithms with different fairness-aware utilities dependent on approval decisions and downstream wealth. Results show that performative dynamics-aware learning with fairness-aware utility that incorporates the downstream outcomes induce better long-term equity and inclusivity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

32 of 54 references.

References · 32

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  4. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  5. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
  6. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  7. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  8. 2020Performative Predictioncited by 318
  9. 2016Recommendations as Treatments: Debiasing Learning and Evaluationcited by 246
  10. 2018Delayed Impact of Fair Machine Learningcited by 183
  11. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 170
  12. 2016Fairness in Learning: Classic and Contextual Banditscited by 167
20 more
  1. 2021Outside the Echo Chamber: Optimizing the Performative Riskcited by 95
  2. 2018The Measure and Mismeasure of Fairnesscited by 94
  3. 2016Fairness in Reinforcement Learningcited by 93
  4. 2019Strategic Classification is Causal Modeling in Disguisecited by 92
  5. 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 55
  6. 2024Fairness Feedback Loops: Training on Synthetic Data Amplifies Biascited by 55
  7. 2018Residual Unfairness in Fair Machine Learning from Prejudiced Datacited by 49
  8. 2022Performative Powercited by 42
  9. 2019Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairnesscited by 38
  10. 2022Performative Reinforcement Learningcited by 25
  11. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 18
  12. 2024Performative Reinforcement Learning in Gradually Shifting Environmentscited by 13
  13. 2023Online Restless Multi-Armed Bandits with Long-Term Fairness Constraintscited by 10
  14. 2022Reinforcement Learning with Stepwise Fairness Constraintscited by 9
  15. 2024Performative Prediction on Games and Mechanism Designcited by 7
  16. 2023Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Ratecited by 6
  17. 2024Active Fourier Auditor for Estimating Distributional Properties of ML Modelscited by 6
  18. 2025Performative Policy Gradient: Optimality in Performative Reinforcement Learningcited by 4
  19. 2021On Meritocracy in Optimal Set Selectioncited by 3
  20. 2025Policy Design in Long-Run Welfare Dynamicscited by 2

Built on by

Not cited yet.