Corpus ID: 209386637

Fair Contextual Multi-Armed Bandits: Theory and Experiments

@inproceedings{Chen2020FairCM,
  title={Fair Contextual Multi-Armed Bandits: Theory and Experiments},
  author={Yifang Chen and Alex Cuellar and Haipeng Luo and Jignesh Modi and Heramb Nemlekar and S. Nikolaidis},
  booktitle={UAI},
  year={2020}
}
  • Yifang Chen, Alex Cuellar, +3 authors S. Nikolaidis
  • Published in UAI 2020
  • Computer Science, Mathematics
  • When an AI system interacts with multiple users, it frequently needs to make allocation decisions. For instance, a virtual agent decides whom to pay attention to in a group setting, or a factory robot selects a worker to deliver a part. Demonstrating fairness in decision making is essential for such systems to be broadly accepted. We introduce a Multi-Armed Bandit algorithm with fairness constraints, where fairness is defined as a minimum rate that a task or a resource is assigned to a user… CONTINUE READING
    4 Citations

    Figures and Topics from this paper.

    Fairness in Learning-Based Sequential Decision Algorithms: A Survey
    • 4
    • PDF
    How Do Fair Decisions Fare in Long-term Qualification?
    Diversity-Preserving K-Armed Bandits, Revisited
    POND: Pessimistic-Optimistic oNline Dispatch

    References

    SHOWING 1-10 OF 25 REFERENCES
    Reinforcement Learning with Fairness Constraints for Resource Distribution in Human-Robot Teams
    • 8
    • PDF
    Fairness in Learning: Classic and Contextual Bandits
    • 219
    • PDF
    Calibrated Fairness in Bandits
    • 52
    • PDF
    Achieving Fairness in the Stochastic Multi-armed Bandit Problem
    • 12
    • Highly Influential
    • PDF
    Combinatorial Sleeping Bandits with Fairness Constraints
    • F. Li, Jia Liu, Bo Ji
    • Computer Science, Mathematics
    • IEEE INFOCOM 2019 - IEEE Conference on Computer Communications
    • 2019
    • 25
    • PDF
    Contextual Bandits with Similarity Information
    • 290
    • PDF
    Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
    • 1,604
    • PDF
    Learning Contextual Bandits in a Non-stationary Environment
    • 29
    • PDF
    Fair Algorithms for Infinite and Contextual Bandits
    • 33
    • PDF
    Multi-armed bandits in metric spaces
    • 335
    • PDF