mlsanityData to 7 Oct 2026

Fairness in Reinforcement Learning

arXiv 1611.03071 ↗First posted 9 Nov 2016cs.LGcited by 93

Not on the map. Why?

Abstract (arXiv)

We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite the fact that fairness is consistent with the optimal policy, any learning algorithm satisfying fairness must take time exponential in the number of states to achieve non-trivial approximation to the optimal policy. We then provide a provably fair polynomial time algorithm under an approximate notion of fairness, thus establishing an exponential gap between exact and approximate fairness

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 15; 2023: 19; 2024: 13; 2025: 9; 2026: 11.

93 papers.

Sort:

By area:

  1. 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
  2. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  3. 2023Datasets and Benchmarks for Offline Safe Reinforcement Learningcited by 58
  4. 2021Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Informationcited by 33
  5. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  6. 2021A Simple Reward-free Approach to Constrained Reinforcement Learningcited by 28
  7. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  8. 2023Long-Term Fairness with Unknown Dynamicscited by 25
  9. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  10. 2021Online certification of preference-based fairness for personalized recommender systemscited by 22
  11. 2021When Fair Ranking Meets Uncertain Inferencecited by 22
  12. 2022Welfare and Fairness in Multi-objective Reinforcement Learningcited by 20
38 more
  1. 2021Unintended Selection: Persistent Qualification Rate Disparities and Interventionscited by 18
  2. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 18
  3. 2022What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspectivecited by 18
  4. 2021Fair Sequential Selection Using Supervised Learning Modelscited by 16
  5. 2021FaiR-IoT: Fairness-aware Human-in-the-Loop Reinforcement Learning for Harnessing Human Variability in Personalized IoTcited by 15
  6. 2021Achieving Counterfactual Fairness for Causal Banditcited by 15
  7. 2023Multi-dimensional discrimination in Law and Machine Learning -- A comparative overviewcited by 15
  8. 2022Survey on Fair Reinforcement Learning: Theory and Practicecited by 14
  9. 2022Socially Fair Reinforcement Learningcited by 13
  10. 2021Towards Return Parity in Markov Decision Processescited by 12
  11. 2023Fair Off-Policy Learning from Observational Datacited by 11
  12. 2021Recommendation Fairness: From Static to Dynamiccited by 10
  13. 2021Fairness with Continuous Optimal Transportcited by 9
  14. 2022Reinforcement Learning with Stepwise Fairness Constraintscited by 9
  15. 2023Fairness in Preference-based Reinforcement Learningcited by 9
  16. 2024Fairness in Reinforcement Learning: A Surveycited by 9
  17. 2021Cooperative Multi-Agent Fairness and Equivariant Policiescited by 8
  18. 2022Multi-disciplinary fairness considerations in machine learning for clinical trialscited by 8
  19. 2022Mitigating Disparity while Maximizing Reward: Tight Anytime Guarantee for Improving Banditscited by 8
  20. 2023Designing Long-term Group Fair Policies in Dynamical Systemscited by 8
  21. 2021Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezingcited by 7
  22. 2021Fairness-aware Online Price Discrimination with Nonparametric Demand Modelscited by 7
  23. 2023Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factorscited by 7
  24. 2023Disentangling and Operationalizing AI Fairness at LinkedIncited by 7
  25. 2023Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Returncited by 7
  26. 2023Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Makingcited by 7
  27. 2021Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environmentcited by 6
  28. 2022Learning Synthetic Environments and Reward Networks for Reinforcement Learningcited by 6
  29. 2021Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instabilitycited by 5
  30. 2021Addressing the Long-term Impact of ML Decisions via Policy Regretcited by 5
  31. 2021Fairer LP-based Online Allocation via Analytic Centercited by 5
  32. 2022Towards Soft Fairness in Restless Multi-Armed Banditscited by 5
  33. 2023Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challengescited by 5
  34. 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spacescited by 5
  35. 2021Statistical discrimination in learning agentscited by 4
  36. 2022Towards Fairness-Aware Multi-Objective Optimizationcited by 4
  37. 2023Group-blind optimal transport to group parity and its constrained variantscited by 4
  38. 2024Striking a Balance in Fairness for Dynamic Systems Through Reinforcement Learningcited by 4

50 most cited of 93 All 93 (JSON)