Almost Envy-Freeness in Group Resource Allocation

Almost Envy-Freeness in Group Resource Allocation

Maria Kyropoulou, Warut Suksompong, Alexandros A. Voudouris

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 400-406. https://doi.org/10.24963/ijcai.2019/57

We study the problem of fairly allocating indivisible goods between groups of agents using the recently introduced relaxations of envy-freeness. We consider the existence of fair allocations under different assumptions on the valuations of the agents. In particular, our results cover cases of arbitrary monotonic, responsive, and additive valuations, while for the case of binary valuations we fully characterize the cardinalities of two groups of agents for which a fair allocation can be guaranteed with respect to both envy-freeness up to one good (EF1) and envy-freeness up to any good (EFX). Moreover, we introduce a new model where the agents are not partitioned into groups in advance, but instead the partition can be chosen in conjunction with the allocation of the goods. In this model, we show that for agents with arbitrary monotonic valuations, there is always a partition of the agents into two groups of any given sizes along with an EF1 allocation of the goods. We also provide an extension of this result to any number of groups.
Keywords:
Agent-based and Multi-agent Systems: Resource Allocation
Agent-based and Multi-agent Systems: Computational Social Choice