EURO 2025 Leeds
Abstract Submission

2770. Fair Compromises in Participatory Budgeting: a Multi-Agent Deep Reinforcement Learning Approach

Invited abstract in session TB-28: Multi-Agent Systems and Reinforcement Learning for Decision Support, stream Decision Support Systems.

Tuesday, 10:30-12:00
Room: Maurice Keyworth 1.03

Authors (first author is the speaker)

1. Hugh Adams

Abstract

Participatory budgeting is a method of collectively understanding and addressing spending priorities where citizens vote on how a budget is spent, it is regularly run to improve the fairness of the distribution of public money. Participatory budgeting requires voters to make decisions on projects, this can lead to "choice overload". A multi-agent reinforcement learning approach to decision support can make decision making easier for voters by pointing towards voting strategies that increase the amount of their vote that wins. This approach can also support policymakers by highlighting aspects of election design that enable fair compromise. This paper presents a novel, ethically aligned approach to decision support using multi-agent deep reinforcement learning modelling. This paper introduces a novel use of a branching neural network architecture to overcome scalability challenges of multi-agent reinforcement learning in a decentralised way. Fair compromise is found through optimising voter actions towards greater representation of voter preferences in the winning set. Experimental evaluation with real-world participatory budgeting data reveals a pattern in fair compromise: that it is achievable through projects with smaller cost.

Keywords

Status: accepted


Back to the list of papers