# Online Fair Revenue Maximizing Cake Division with Non-Contiguous Pieces in Adversarial Bandits

arXiv: https://arxiv.org/abs/2111.14387 · HTML: https://mlsanity.com/paper/2111.14387/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 29 Nov 2021.

## Builds on (most cited first, 7 of 7)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Fairness of Exposure in Stochastic Bandits](https://mlsanity.com/paper/2103.02735/) (2021)
- [Advancing subgroup fairness via sleeping experts](https://mlsanity.com/paper/1909.08375/) (2019)
- [Fair Algorithms for Infinite and Contextual Bandits](https://mlsanity.com/paper/1610.09559/) (2016)
- [On preserving non-discrimination when combining expert advice](https://mlsanity.com/paper/1810.11829/) (2018)

## Built on by (most cited first, 2 of 2)

- [Survey on Fair Reinforcement Learning: Theory and Practice](https://mlsanity.com/paper/2205.10032/) (2022)
- [Fairness in Reinforcement Learning: A Survey](https://mlsanity.com/paper/2405.06909/) (2024)

## Abstract (arXiv)

The classic cake-cutting problem provides a model for addressing the fair and efficient allocation of a divisible, heterogeneous resource among agents with distinct preferences. Focusing on a standard formulation of cake cutting, in which each agent must receive a contiguous piece of the cake in an offline setting, this work instead focuses on online allocating non-contiguous pieces of cake among agents and establishes algorithmic results for fairness measures. In this regard, we made use of classic adversarial multi-armed bandits to achieve sub-linear Fairness and Revenue Regret at the same time. Adversarial bandits are powerful tools to model the adversarial reinforcement learning environments, that provide strong upper-bounds for regret of learning with just observing one action's reward in each step by applying smart trade-off between exploration and exploitation. This work studies the power of the famous EXP_3 algorithm that is based on exponential wight{-}importance updating probability distribution through time horizon.