mlsanityData to 14 Oct 2026

Group Fairness in Multi-Task Reinforcement Learning

arXiv 2503.07817 ↗First posted 10 Mar 2025cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

This paper addresses a critical societal consideration in the application of Reinforcement Learning (RL): ensuring equitable outcomes across different demographic groups in multi-task settings. While previous work has explored fairness in single-task RL, many real-world applications are multi-task in nature and require policies to maintain fairness across all tasks. We introduce a novel formulation of multi-task group fairness in RL and propose a constrained optimization algorithm that explicitly enforces fairness constraints across multiple tasks simultaneously. We have shown that our proposed algorithm does not violate fairness constraints with high probability and with sublinear regret in the finite-horizon episodic setting. Through experiments in RiverSwim and MuJoCo environments, we demonstrate that our approach better ensures group fairness across multiple tasks compared to previous methods that lack explicit multi-task fairness constraints in both the finite-horizon setting and the infinite-horizon setting. Our results show that the proposed algorithm achieves smaller fairness gaps while maintaining comparable returns across different demographic groups and tasks, suggesting its potential for addressing fairness concerns in real-world multi-task RL applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 22 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

15 of 22 references.

References · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2017A Survey on Multi-Task Learningcited by 840
  4. 2015Risk-Constrained Reinforcement Learning with Percentile Risk Criteriacited by 337
  5. 2018Top-K Off-Policy Correction for a REINFORCE Recommender Systemcited by 182
  6. 2017Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learningcited by 176
  7. 2018Deep Reinforcement Learning for Page-wise Recommendationscited by 100
  8. 2015Inferring Networks of Substitutable and Complementary Productscited by 92
  9. 2021Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPscited by 80
  10. 2021Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learningcited by 34
  11. 2023Long-Term Fairness with Unknown Dynamicscited by 27
  12. 2022Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systemscited by 14
3 more
  1. 2021Towards Return Parity in Markov Decision Processescited by 13
  2. 2022Learning to Teach Fairness-aware Deep Multi-task Learningcited by 8
  3. 2021Reinforced Workload Distribution Fairnesscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Fairness in Reinforcement Learning: A Survey
  2. 2023Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning
  3. 2024Fairness in Reinforcement Learning with Bisimulation Metrics
  4. 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
  5. 2025AdaFair-MARL: Enforcing Adaptive Fairness Constraints in Multi-Agent Reinforcement Learning
  6. 2024Fair Resource Allocation in Multi-Task Learning
  7. 2025Towards Reward Fairness in RLHF: From a Resource Allocation Perspective
  8. 2025PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing